© 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. 53837
    Prev
    Next
    INDEX
    Explanations

    code/documentation

    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
    itness
    -0.29
    年代
    -0.26
     affili
    -0.25
    abit
    -0.25
    éĻħ
    -0.25
     Ward
    -0.24
    eting
    -0.24
     invitations
    -0.24
    adh
    -0.24
    汪
    -0.24
    POSITIVE LOGITS
     <<↵
    0.26
     ($)
    0.26
     drastically
    0.25
     dramatically
    0.24
     license
    0.24
     Humanities
    0.24
     SYMBOL
    0.23
    roz
    0.23
    icc
    0.23
     myfile
    0.23
    Activations Density 0.019%

    No Known Activations