© 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. 57552
    Prev
    Next
    INDEX
    Explanations

    not

    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
     understanding
    -0.31
     comprend
    -0.29
    uggest
    -0.28
    åIJĥäºı
    -0.27
     unaware
    -0.27
    ä¹ŁçŁ¥éģĵ
    -0.27
    äºİ
    -0.27
     understood
    -0.26
    ä¸įçŁ¥éģĵ
    -0.26
     awareness
    -0.26
    POSITIVE LOGITS
    _ZONE
    0.33
    ernote
    0.29
    GRAM
    0.26
    ylene
    0.26
    tement
    0.26
     Associated
    0.26
    _Native
    0.25
    alement
    0.25
    ffc
    0.25
    onte
    0.24
    Activations Density 0.006%

    No Known Activations