© 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. 53336
    Prev
    Next
    INDEX
    Explanations

    broken or damaged things

    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
    eer
    -0.26
    figure
    -0.26
    ERT
    -0.25
    åĩĨ
    -0.25
    BaseContext
    -0.24
     kernels
    -0.24
    å¤©åľ°
    -0.24
    éļıçĿĢ
    -0.24
    mát
    -0.24
    themes
    -0.23
    POSITIVE LOGITS
    clo
    0.30
    _hat
    0.26
     fr
    0.26
    å¿ĥè¡Ģ
    0.26
    Showing
    0.25
    illon
    0.25
    _frm
    0.25
    ç¦ıç¥ī
    0.24
     Cata
    0.24
     optim
    0.24
    Activations Density 0.019%

    No Known Activations