© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 39926
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    亿åħĥ以ä¸Ĭ
    -0.27
    ettel
    -0.27
     ########################################################################
    -0.27
     gén
    -0.25
     Chrom
    -0.25
     nucle
    -0.24
    è¿Ļæľ¬ä¹¦
    -0.24
    ecal
    -0.24
     déco
    -0.24
    zt
    -0.23
    POSITIVE LOGITS
    æĸ¡
    0.27
    itarian
    0.26
    é½IJ
    0.25
    好æ¶Īæģ¯
    0.25
     -↵
    0.25
    izen
    0.25
     rav
    0.24
    åıįä¹ĭ
    0.24
    mes
    0.24
    roperty
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.