© 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. 39002
    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
     ÑĤоÑĢ
    -0.31
     Innovative
    -0.30
     unavoidable
    -0.29
     Seas
    -0.27
    ANI
    -0.26
     дела
    -0.26
     explan
    -0.26
    ÑĨе
    -0.26
    CORD
    -0.25
    Ñģел
    -0.25
    POSITIVE LOGITS
    åİŁæłĩé¢ĺ
    0.31
    çĭ¬
    0.30
    alt
    0.29
    ell
    0.29
    驾
    0.28
    åı³ä¾§
    0.28
    ym
    0.28
    ixon
    0.26
    ol
    0.26
    alem
    0.26
    Activations Density 9.361%

    No Known Activations

    This feature has no known activations.