© 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. 24-TRANSCODER-HP
    7. 150285
    Prev
    Next
    INDEX
    Explanations

    programming/code errors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orning
    -0.29
    ochen
    -0.26
    icion
    -0.26
    çŁŃ
    -0.26
    ponsors
    -0.25
    icken
    -0.25
     acknow
    -0.24
    pch
    -0.24
    è±ļ
    -0.24
    asonic
    -0.24
    POSITIVE LOGITS
     mere
    0.30
     repertoire
    0.27
    åij½é¢ĺ
    0.26
     appeal
    0.25
     laboratory
    0.25
     IO
    0.25
     bott
    0.24
    妥
    0.24
     labor
    0.24
     Arrays
    0.23
    Activations Density 0.078%

    No Known Activations