© 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. 52922
    Prev
    Next
    INDEX
    Explanations

    Code and numerical data

    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
    Ù«
    -0.31
    åįĬ
    -0.29
    åįĬ个
    -0.27
    elage
    -0.26
    .xx
    -0.26
    æĬ±
    -0.25
    ãĤ«ãĥ«
    -0.25
     intuit
    -0.24
    ½
    -0.24
    pons
    -0.24
    POSITIVE LOGITS
    çŃ¹å¤ĩ
    0.28
    åĿĤ
    0.26
    arp
    0.24
     Memorial
    0.24
     fatally
    0.24
    ixel
    0.24
    åĽŀåIJĪ
    0.24
    zer
    0.23
    åľ¨å½ĵåľ°
    0.23
    shopping
    0.23
    Activations Density 0.183%

    No Known Activations