© 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. 22-TRANSCODER-HP
    7. 112480
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     transit
    -0.29
    åİ¢
    -0.27
    éĹ´æİ¥
    -0.26
     trans
    -0.26
    grad
    -0.24
    eks
    -0.24
     pend
    -0.24
     Transit
    -0.24
    好å¤Ħ
    -0.24
     Trans
    -0.23
    POSITIVE LOGITS
    pedia
    0.30
    ptic
    0.27
     DPI
    0.26
     spotlight
    0.25
    resas
    0.25
    iente
    0.24
    artner
    0.24
    åIJĪãģĦ
    0.24
    nej
    0.24
     attempt
    0.24
    Activations Density 0.006%

    No Known Activations

    This feature has no known activations.