© 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. 39370
    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
     communications
    -0.25
    shade
    -0.25
    å¼Ĥè®®
    -0.25
     shading
    -0.25
    bal
    -0.24
     Shed
    -0.24
    纹
    -0.24
    AZE
    -0.24
     Aph
    -0.24
     strangers
    -0.23
    POSITIVE LOGITS
    isoft
    0.32
    avar
    0.26
    èĥ½åĬĽåĴĮ
    0.25
    (stack
    0.25
    incer
    0.25
    ÑİÑģÑĮ
    0.24
    á»ħn
    0.24
     redo
    0.24
    讲
    0.24
    FullYear
    0.24
    Activations Density 0.045%

    No Known Activations

    This feature has no known activations.