© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7847
    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
    èĤ²
    -0.27
    çĦī
    -0.26
    rez
    -0.24
    Pipe
    -0.24
    ])]
    -0.24
    .Predicate
    -0.24
     fran
    -0.24
    :NS
    -0.23
    rowned
    -0.23
     rez
    -0.23
    POSITIVE LOGITS
    atus
    0.28
    ä¸įè¦ģ太
    0.25
    ifax
    0.25
    icing
    0.25
    ref
    0.24
    walking
    0.24
    祥
    0.24
    opus
    0.24
    worker
    0.24
    è¿ĽæŃ¥
    0.24
    Activations Density 0.059%

    No Known Activations