© 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. 32-TRANSCODER-HP
    7. 41839
    Prev
    Next
    INDEX
    Explanations

    on

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     appar
    -0.30
     zipfile
    -0.28
    ilver
    -0.25
    å±Ī
    -0.25
    azu
    -0.24
    æīĵåĩ»
    -0.24
    弯
    -0.24
     reluct
    -0.24
     Byte
    -0.24
    ROSS
    -0.24
    POSITIVE LOGITS
     equivalent
    0.27
    irs
    0.27
     equal
    0.27
     commuting
    0.25
    ÑıÑģ
    0.25
    æĬ±
    0.25
     perfect
    0.24
     heraus
    0.24
     committing
    0.24
     crystall
    0.24
    Activations Density 0.001%

    No Known Activations