© 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. 8185
    Prev
    Next
    INDEX
    Explanations

    Information extraction

    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
     Sponsor
    -0.28
    饶
    -0.28
    _flow
    -0.27
    çļĦæĿĥåĪ©
    -0.26
    loat
    -0.26
    .flow
    -0.25
    [np
    -0.25
    礼仪
    -0.25
     obligations
    -0.25
     evaluator
    -0.25
    POSITIVE LOGITS
    é«ĺæķĪçļĦ
    0.40
    é«ĺæķĪ
    0.38
    _ability
    0.33
     techniques
    0.32
    èĥ½åĬĽå¼º
    0.32
    æķĪçİĩ
    0.31
    Eff
    0.31
    çģ«åĬĽ
    0.31
    æİĮæı¡äºĨ
    0.31
    éģĭçĶ¨
    0.31
    Activations Density 0.000%

    No Known Activations