© 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. 27-TRANSCODER-HP
    7. 57839
    Prev
    Next
    INDEX
    Explanations

    slavery

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avian
    -0.35
    æľįåĬ¡æ°´å¹³
    -0.25
    åīįèĢħ
    -0.25
    ogs
    -0.25
    çļĦç¨ĭ度
    -0.24
    iline
    -0.24
    оÑĦ
    -0.23
    çļĦåĵģçīĮ
    -0.23
    太åŃIJ
    -0.23
    itten
    -0.23
    POSITIVE LOGITS
    -hooks
    0.30
    æī©å¼ł
    0.28
    casting
    0.26
    æī©
    0.26
    .xr
    0.25
     minded
    0.25
    ãĤ³ãĥ¼
    0.24
    _RSA
    0.24
    CAST
    0.24
    rollers
    0.24
    Activations Density 0.031%

    No Known Activations