© 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. 5839
    Prev
    Next
    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    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
    gee
    -0.27
    æijĩäºĨ
    -0.27
    plant
    -0.26
    çĤ¹åĩ»æŁ¥çľĭ
    -0.26
    _printf
    -0.25
     thanked
    -0.25
     Schul
    -0.25
    awn
    -0.25
     дл
    -0.24
    chner
    -0.24
    POSITIVE LOGITS
     vol
    0.27
     probabil
    0.26
     accord
    0.26
    vol
    0.26
    agh
    0.25
    ile
    0.25
    iles
    0.25
     various
    0.24
    .vol
    0.24
    ä»ģ
    0.24
    Activations Density 0.024%

    No Known Activations