© 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. 39325
    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
    åĽ½åĬ¡
    -0.31
    ersh
    -0.27
    orer
    -0.27
    _PRIMARY
    -0.26
     zob
    -0.26
    ovy
    -0.26
     Immutable
    -0.26
    assage
    -0.26
    odable
    -0.26
     unten
    -0.25
    POSITIVE LOGITS
    ĮĢ
    0.29
    æ¯į
    0.27
     pa
    0.27
    对æĬĹ
    0.26
     Tem
    0.25
    bris
    0.24
    èĩª
    0.24
    demo
    0.24
    ñ
    0.24
    ina
    0.24
    Activations Density 3.161%

    No Known Activations

    This feature has no known activations.