© 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. 53759
    Prev
    Next
    INDEX
    Explanations

    b

    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
    LO
    -0.26
    ÙĬب
    -0.26
    å®¡æł¸
    -0.25
     Lag
    -0.25
     sen
    -0.24
    åĿij
    -0.24
    ä¸ī代
    -0.24
    ental
    -0.24
    punk
    -0.24
    cab
    -0.23
    POSITIVE LOGITS
    .ep
    0.28
     Cary
    0.27
     abstract
    0.27
    æĻ¶ä½ĵ
    0.26
    åĽºä½ĵ
    0.26
    asses
    0.26
    ophilia
    0.25
    ARDS
    0.25
     Locker
    0.25
    ä¸ĭæĿ¥çļĦ
    0.25
    Activations Density 0.790%

    No Known Activations