© 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. 5454
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     zero
    -0.27
     tires
    -0.26
    _zero
    -0.26
    afka
    -0.25
     keys
    -0.25
    Zero
    -0.24
    dm
    -0.24
     dm
    -0.24
     zeros
    -0.24
     tyres
    -0.24
    POSITIVE LOGITS
     ^.
    0.25
     *&
    0.24
    åı¯èĥ½æĢ§
    0.24
    part
    0.24
    .real
    0.24
    ç³
    0.24
     Corm
    0.23
    å¸IJ
    0.23
    oron
    0.23
    ä¸įç»ı
    0.23
    Activations Density 0.031%

    No Known Activations