© 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. 141273
    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
    جة
    -0.28
    说çĿĢ
    -0.28
    说èĩªå·±
    -0.27
    å½ĵãģŁãĤĬåīį
    -0.26
    ä¸Ĭä¸ĭ游
    -0.26
    ÑįÑĢ
    -0.25
     formed
    -0.24
    rection
    -0.24
    standing
    -0.24
    ç§ī
    -0.23
    POSITIVE LOGITS
    nam
    0.30
    atoria
    0.28
    ogi
    0.28
    æıIJè®®
    0.27
     laz
    0.27
    nice
    0.26
    \\/
    0.26
    失åİ»
    0.25
    æĻļæľŁ
    0.25
    çĸ²åĬ³
    0.25
    Activations Density 8.690%

    No Known Activations

    This feature has no known activations.