© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6661
    Prev
    Next
    INDEX
    Explanations

    the

    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
    #a
    -0.28
    èĭ´
    -0.28
    abal
    -0.25
     khẩu
    -0.24
    ç»ĪçĤ¹
    -0.23
    Partial
    -0.23
    #index
    -0.23
    ling
    -0.23
    Rh
    -0.23
    éĢī
    -0.23
    POSITIVE LOGITS
    åı¯æĥ³
    0.26
    vince
    0.26
    ocity
    0.25
    actable
    0.24
    ophys
    0.24
    apons
    0.24
     agreement
    0.24
    odon
    0.24
    /API
    0.24
     во
    0.24
    Activations Density 0.021%

    No Known Activations