© 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. 33-TRANSCODER-HP
    7. 53519
    Prev
    Next
    INDEX
    Explanations

    fasting

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fast
    -1.33
    fast
    -1.22
     Fast
    -1.14
    Fast
    -1.09
    -fast
    -1.05
    å¿«
    -1.05
    _fast
    -0.90
    /fast
    -0.87
     FAST
    -0.87
    FAST
    -0.85
    POSITIVE LOGITS
    åij³
    0.26
    éķĴ
    0.24
     dif
    0.24
    ç¼ĸçłģ
    0.24
    ltr
    0.24
    .osgi
    0.23
    æ¦Ľ
    0.23
    Altern
    0.23
    oro
    0.23
    %E
    0.23
    Activations Density 0.010%

    No Known Activations