© 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. 5242
    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
     SAL
    -0.29
    ik
    -0.29
     Urg
    -0.27
    订éĺħ
    -0.27
    å¡ĺ
    -0.27
    æľį
    -0.25
     pul
    -0.25
     sole
    -0.25
     only
    -0.25
     Only
    -0.25
    POSITIVE LOGITS
    ivities
    0.30
    EMU
    0.27
    éĻªä½ł
    0.26
     IPAddress
    0.26
     %=
    0.26
    ewood
    0.25
    posable
    0.25
    posé
    0.24
    åIJŃ
    0.24
    xmm
    0.24
    Activations Density 0.354%

    No Known Activations

    This feature has no known activations.