© 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. 5744
    Prev
    Next
    INDEX
    Explanations

    frequency

    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
     fewer
    -0.30
    qing
    -0.29
    iere
    -0.27
    ä»ĸçŁ¥éģĵ
    -0.27
    ÑģÑĤвенно
    -0.26
    ä¸įåĩĨ
    -0.26
     Rai
    -0.26
    acho
    -0.25
    ieri
    -0.25
    ÑģÑĤв
    -0.25
    POSITIVE LOGITS
     option
    0.26
    ç³ł
    0.25
    lse
    0.25
     arrow
    0.24
     seams
    0.24
    .bat
    0.24
     contest
    0.23
    æĥ°
    0.23
    åIJ¸åħ¥
    0.23
     Concat
    0.23
    Activations Density 0.004%

    No Known Activations