© 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. 24874
    Prev
    Next
    INDEX
    Explanations

    from

    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
    èĩªå·±çļĦ
    -0.79
    èĩªå·±
    -0.75
     own
    -0.72
     yourself
    -0.66
     oneself
    -0.66
    äºĨèĩªå·±çļĦ
    -0.63
    èĩªèº«çļĦ
    -0.61
    ç»Ļèĩªå·±
    -0.59
     myself
    -0.59
     herself
    -0.57
    POSITIVE LOGITS
     biá»ĩt
    0.29
     Critics
    0.28
    tester
    0.26
    .Executor
    0.25
    panic
    0.25
    atura
    0.24
    izr
    0.24
     vocab
    0.24
    pill
    0.24
    alia
    0.23
    Activations Density 0.000%

    No Known Activations