© 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. 5406
    Prev
    Next
    INDEX
    Explanations

    Numbers

    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
    éľĢè¦ģçĶ¨
    -0.29
    bout
    -0.27
     |/
    -0.26
    uja
    -0.26
     -*
    -0.26
    ouchers
    -0.26
     wives
    -0.25
    wives
    -0.25
    bac
    -0.24
    çĶ¨äºİ
    -0.24
    POSITIVE LOGITS
    rale
    0.27
    dale
    0.26
    ä¸įåĪ°
    0.25
    éģĹçķĻ
    0.24
    çľĭ好
    0.24
     dock
    0.24
     remaining
    0.23
     maint
    0.23
    çĭ¸
    0.23
     McGr
    0.23
    Activations Density 0.008%

    No Known Activations