© 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. 20-TRANSCODER-HP
    7. 63421
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    irit
    -0.29
    äºĴ
    -0.28
    å¿ĥçIJĨ
    -0.27
    缴è¨Ģ
    -0.26
    _Char
    -0.26
    è°Ħ
    -0.26
    .Scanner
    -0.25
    æŀ¥
    -0.25
    åĵģ
    -0.24
    gte
    -0.24
    POSITIVE LOGITS
     penn
    0.27
    æľŃ
    0.27
     meaningless
    0.26
    ç³Ĭæ¶Ĥ
    0.26
    ação
    0.26
    _VAL
    0.25
    çİĩè¾¾
    0.25
    eworthy
    0.25
    éģĩéļ¾
    0.24
    ellung
    0.24
    Activations Density 4.839%

    No Known Activations

    This feature has no known activations.