© 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. 23-TRANSCODER-HP
    7. 23836
    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_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è°Ł
    -0.27
    设æľī
    -0.27
    åıĶ
    -0.27
     being
    -0.26
    .openg
    -0.26
    åŃĶ
    -0.26
    åĩ¶
    -0.25
    주ìĿĺ
    -0.25
    éĮ¯
    -0.25
    amy
    -0.25
    POSITIVE LOGITS
     loaf
    0.30
    nze
    0.29
     replen
    0.25
    æĶ¯éħį
    0.24
    loquent
    0.24
    ermint
    0.24
    ZE
    0.24
    ProgressHUD
    0.23
     pars
    0.23
     rehe
    0.23
    Activations Density 0.002%

    No Known Activations