© 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. 39950
    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
    æĥ¯
    -0.26
    erals
    -0.26
    SCAN
    -0.25
    érc
    -0.25
    ROTO
    -0.25
    emodel
    -0.24
    ä¼Ļ
    -0.24
    è®°å¾Ĺ
    -0.24
    å®Į
    -0.24
    çļ±çº¹
    -0.24
    POSITIVE LOGITS
    ê°ģ
    0.27
    ibility
    0.25
     caused
    0.24
    æľ¬æĸĩ
    0.24
     themselves
    0.24
    å¼ķèµ·
    0.23
    绢
    0.23
    大èĩªçĦ¶
    0.23
    anka
    0.23
    å¼Ģåĩº
    0.23
    Activations Density 4.115%

    No Known Activations

    This feature has no known activations.