© 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. 7588
    Prev
    Next
    INDEX
    Explanations

    Code

    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
    CENTER
    -0.30
     Rede
    -0.27
    ä¹Łå¥½
    -0.26
    _centers
    -0.26
    ,response
    -0.25
    _trampoline
    -0.25
     centers
    -0.24
    arsi
    -0.24
    ibern
    -0.23
     HttpResponseMessage
    -0.23
    POSITIVE LOGITS
     slice
    0.25
    èĸ¤
    0.25
    stroy
    0.25
    zyst
    0.24
    çĽ¸äº²
    0.24
    eken
    0.24
    çĴĭ
    0.24
    ertos
    0.23
    belt
    0.23
    .Assertions
    0.23
    Activations Density 0.014%

    No Known Activations