© 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. 7121
    Prev
    Next
    INDEX
    Explanations

    constraint

    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
    hausen
    -0.23
    avana
    -0.23
    traits
    -0.23
    cour
    -0.23
    izens
    -0.22
     ÑģамÑĭе
    -0.22
     każ
    -0.21
     getService
    -0.21
    éķ¿çŁŃ
    -0.21
    åķ¡
    -0.21
    POSITIVE LOGITS
    OI
    0.27
     Lambert
    0.26
     Archer
    0.23
    ÅĽci
    0.23
    elist
    0.23
    nel
    0.23
    ÃŃm
    0.22
    迤
    0.22
    Initializer
    0.22
    scriber
    0.22
    Activations Density 4.260%

    No Known Activations