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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5204
    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
    模
    -0.33
    Parms
    -0.27
    æ³½
    -0.26
    æĸĩä¸Ń
    -0.25
    pace
    -0.25
    fl
    -0.25
    æĪ·
    -0.25
    æ¯į
    -0.25
    缩
    -0.25
    åĪĨæĺİ
    -0.24
    POSITIVE LOGITS
    RESSED
    0.27
    æĪ¾
    0.25
    èµĤ
    0.25
    niejs
    0.25
     Nass
    0.24
    venues
    0.24
    éĵĻ
    0.24
    iances
    0.24
     bitten
    0.24
     Diploma
    0.24
    Activations Density 0.009%

    No Known Activations

    This feature has no known activations.