© 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. 53655
    Prev
    Next
    INDEX
    Explanations

    makes sense

    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
    actly
    -0.30
    chas
    -0.27
    ashington
    -0.27
    lectic
    -0.27
    ķĮ
    -0.26
    \Test
    -0.26
    ilyn
    -0.25
    \-
    -0.25
    HttpException
    -0.24
    è¿ģ移
    -0.24
    POSITIVE LOGITS
     their
    0.32
    ä»ĸ们çļĦ
    0.31
    their
    0.30
    Their
    0.28
    they
    0.28
     degree
    0.28
    degree
    0.28
     nuestros
    0.27
    ä»ĸ们
    0.26
     loro
    0.26
    Activations Density 0.014%

    No Known Activations