© 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. 53742
    Prev
    Next
    INDEX
    Explanations

    uh

    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
     care
    -0.27
    ,response
    -0.26
    reten
    -0.26
    ustr
    -0.25
     impro
    -0.25
    tdown
    -0.25
     rh
    -0.24
    jsonp
    -0.24
    orate
    -0.24
    VML
    -0.24
    POSITIVE LOGITS
    æ³ķå¾ĭæ³ķè§Ħ
    0.29
    fir
    0.28
    åijĬ
    0.27
    åħ¬æ°ij
    0.27
    asti
    0.26
     laying
    0.25
    å±Ģ
    0.25
    åħ¬ç½ij
    0.25
    ahr
    0.25
    åŀĭä¼ģä¸ļ
    0.24
    Activations Density 0.011%

    No Known Activations