© 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. 5278
    Prev
    Next
    INDEX
    Explanations

    to

    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
    urai
    -0.28
    æ½®
    -0.26
    hea
    -0.26
     recipient
    -0.26
    zo
    -0.26
    erea
    -0.26
    arı
    -0.26
     invers
    -0.25
    ara
    -0.25
     equally
    -0.25
    POSITIVE LOGITS
    è´¯
    0.29
     Owned
    0.27
    aleur
    0.26
     herself
    0.26
    usable
    0.26
    -owned
    0.25
     owned
    0.25
    angible
    0.24
    never
    0.24
    ç®ĹäºĨ
    0.24
    Activations Density 0.009%

    No Known Activations