© 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. 39298
    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
    sı
    -0.28
    elsea
    -0.27
    æĪĸå¤ļ
    -0.26
    UGINS
    -0.25
    PLIER
    -0.25
    leanor
    -0.25
    edian
    -0.24
    DialogTitle
    -0.24
    rı
    -0.24
     localVar
    -0.24
    POSITIVE LOGITS
    åıĹéĻIJ
    0.31
    èµ·ä¼ı
    0.27
     Smith
    0.25
     smith
    0.24
    åħ«åį¦
    0.24
     His
    0.24
    Structured
    0.24
    :length
    0.24
    orem
    0.24
    纵横
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.