© 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. 27-TRANSCODER-HP
    7. 8541
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æīĢ以
    -0.32
    åĨĴçĿĢ
    -0.29
    æ»ĥ
    -0.27
    earer
    -0.27
    æīĢä»¥åľ¨
    -0.26
    ië
    -0.26
    (so
    -0.26
    /browse
    -0.26
    assage
    -0.26
    berger
    -0.25
    POSITIVE LOGITS
     physical
    0.30
     physically
    0.29
    为大家
    0.28
     Pit
    0.27
    欢è¿İæĤ¨
    0.27
    ="../../../
    0.26
    physical
    0.26
     fair
    0.26
    gger
    0.25
    Physical
    0.25
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.