© 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. 8304
    Prev
    Next
    INDEX
    Explanations

    code/software text

    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
    弥补
    -0.28
    lsruhe
    -0.24
     },{
    -0.24
    ãģijãģ°
    -0.24
    [assembly
    -0.24
     Metropolitan
    -0.24
    è°ķ
    -0.24
    everything
    -0.23
    -License
    -0.23
     respectfully
    -0.23
    POSITIVE LOGITS
     Til
    0.26
     Shadow
    0.25
     Hazel
    0.24
    dff
    0.24
    Shadow
    0.24
     avent
    0.23
    蹶
    0.23
    spath
    0.23
     Petro
    0.23
    解æĶ¾æĢĿæĥ³
    0.23
    Activations Density 0.008%

    No Known Activations