© 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. 30-TRANSCODER-HP
    7. 95746
    Prev
    Next
    INDEX
    Explanations

    periods

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yll
    -0.30
    å¸Ľ
    -0.27
     JText
    -0.26
    arrays
    -0.26
     Posting
    -0.25
    abric
    -0.25
    让æĪij
    -0.25
    å¿ĥéĩĮ
    -0.24
    ä¸ĢéŨ
    -0.24
    ä¸ĵ线
    -0.24
    POSITIVE LOGITS
     re
    0.41
    éĩįæĸ°
    0.38
     repl
    0.34
     thesis
    0.33
    éĩįæķ´
    0.32
    éĩįç»Ħ
    0.30
     rethink
    0.29
    inate
    0.28
     rewrite
    0.28
    _IDENT
    0.28
    Activations Density 0.904%

    No Known Activations