© 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. 56767
    Prev
    Next
    INDEX
    Explanations

    Legal documents

    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
    lash
    -0.27
     destruct
    -0.26
    견
    -0.25
    ç½ijç«Ļåľ°åĽ¾
    -0.24
    meg
    -0.24
    -haspopup
    -0.24
     initComponents
    -0.24
    éŨçªĹ
    -0.23
    ature
    -0.23
    è¯ł
    -0.23
    POSITIVE LOGITS
    çĵ¶åŃIJ
    0.28
    çļĦæĥħæĦŁ
    0.28
    ROC
    0.27
    éŃĤ
    0.26
    æĹ¶ç©º
    0.26
    åĨĽåĽ¢
    0.25
    Period
    0.25
    å®ŀæŶ
    0.25
     correlations
    0.25
    تارÙĬØ®
    0.25
    Activations Density 0.002%

    No Known Activations