© 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. 39739
    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
    icorn
    -0.29
     saja
    -0.26
    åħ¨æĸĩ
    -0.25
    ][-
    -0.24
    éħIJ
    -0.24
    浯
    -0.24
     Sit
    -0.24
    Canon
    -0.23
    cth
    -0.23
    olland
    -0.23
    POSITIVE LOGITS
    ç»ĺçĶ»
    0.24
    è¡Į车
    0.24
    èĢ¦
    0.23
    èĴĻ
    0.23
    è´©
    0.23
     tie
    0.23
    åĬĩ
    0.23
    autiful
    0.23
    ạn
    0.23
    reu
    0.23
    Activations Density 20.014%

    No Known Activations

    This feature has no known activations.