© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6401
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CBC
    -0.28
    é»ij客
    -0.27
    grades
    -0.26
    validators
    -0.26
    inand
    -0.25
    pta
    -0.24
     Bolton
    -0.24
    ç»Ĩå¿ĥ
    -0.24
    igans
    -0.24
    efe
    -0.24
    POSITIVE LOGITS
    å½ĵä¹ĭ
    0.29
     behind
    0.26
     Marg
    0.25
    owing
    0.24
     meg
    0.24
     Behind
    0.24
     symbol
    0.24
     gib
    0.24
    çĥŃ度
    0.24
    å¾ĭå¸ĪäºĭåĬ¡
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.