© 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. 53700
    Prev
    Next
    INDEX
    Explanations

    the

    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
    åĢĴéľī
    -0.27
    unger
    -0.27
    caught
    -0.26
    é»ijåIJįåįķ
    -0.26
    æİĴæ°´
    -0.25
    é¤IJæ¡Į
    -0.25
     lá»Ńa
    -0.25
    thalm
    -0.25
    TypeError
    -0.25
    ËĮ
    -0.24
    POSITIVE LOGITS
     activity
    0.37
     relation
    0.31
     program
    0.30
     experiment
    0.29
     relations
    0.29
     age
    0.29
     suspect
    0.29
     condition
    0.28
     partnership
    0.28
     ages
    0.28
    Activations Density 0.024%

    No Known Activations