© 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. 54329
    Prev
    Next
    INDEX
    Explanations

    German and code

    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
     feature
    -0.40
     features
    -0.38
     FEATURE
    -0.33
     Feature
    -0.33
     Features
    -0.33
    .features
    -0.32
    _feat
    -0.32
    .feature
    -0.31
    FEATURE
    -0.31
    features
    -0.31
    POSITIVE LOGITS
    le
    0.31
     unre
    0.29
    lei
    0.27
    sten
    0.26
     star
    0.26
    æĿłæĿĨ
    0.26
    lev
    0.26
    oga
    0.25
    æį¢
    0.25
    (le
    0.25
    Activations Density 0.017%

    No Known Activations