© 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. 5980
    Prev
    Next
    INDEX
    Explanations

    scientific abstracts

    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
    ACA
    -0.31
    aro
    -0.27
    rench
    -0.27
    èĢĮä¸Ķè¿ĺ
    -0.27
    BaseContext
    -0.26
    éħĨ
    -0.26
     Braun
    -0.25
     axe
    -0.25
    allen
    -0.25
     Entered
    -0.24
    POSITIVE LOGITS
    ku
    0.27
    åĬĪ
    0.24
    大åĨĽ
    0.24
     Nab
    0.23
    ads
    0.23
    åĬ«
    0.23
    大æĪĺ
    0.23
    å·¥ç¨ĭ
    0.23
    mn
    0.23
     pics
    0.23
    Activations Density 0.021%

    No Known Activations