© 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. 5771
    Prev
    Next
    INDEX
    Explanations

    News articles/opinion

    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
    phans
    -0.27
    å¸ĪåĤħ
    -0.26
    SR
    -0.26
     onCreateOptionsMenu
    -0.25
    _masks
    -0.24
    occasion
    -0.24
    contr
    -0.24
    SA
    -0.24
    umer
    -0.24
     å¿
    -0.24
    POSITIVE LOGITS
    æĦŁæ¿Ģ
    0.27
    åĢĻéĢī人
    0.26
     Programme
    0.25
    æĢĢæĬ±
    0.25
    quin
    0.24
    夷
    0.24
    riot
    0.24
    splice
    0.24
    quo
    0.23
    xmin
    0.23
    Activations Density 0.009%

    No Known Activations