© 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. 32-TRANSCODER-HP
    7. 41714
    Prev
    Next
    INDEX
    Explanations

    Must

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     w
    -0.75
    w
    -0.48
    "w
    -0.42
    =w
    -0.41
     dim
    -0.41
    	w
    -0.37
    .w
    -0.36
    ï½Ĺ
    -0.36
    (w
    -0.36
    dim
    -0.35
    POSITIVE LOGITS
    妣
    0.28
    ลà¸ĩ
    0.27
    unsch
    0.26
    ä¸ĭåįĬ
    0.26
    èIJ½åľ°
    0.25
    .putText
    0.25
    (drop
    0.25
     crest
    0.25
    æĹłåĬĽ
    0.25
    ä¸įèĪĴæľį
    0.24
    Activations Density 0.002%

    No Known Activations