© 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. 54129
    Prev
    Next
    INDEX
    Explanations

    -striped

    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
    å¹ħ
    -0.28
    ulet
    -0.28
     poles
    -0.26
    æĭľå¸Ī
    -0.26
    .zoom
    -0.26
    ç²Ĵ
    -0.25
     Mug
    -0.25
    è±Ĩ
    -0.25
    鸵
    -0.24
     Moo
    -0.24
    POSITIVE LOGITS
    åij½
    0.29
    swire
    0.29
    bral
    0.27
    spl
    0.26
    itors
    0.25
    ä¸Ŀ绸
    0.24
    spath
    0.24
    åĨµ
    0.24
     Patron
    0.24
    ivated
    0.24
    Activations Density 0.004%

    No Known Activations