© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 33162
    Prev
    Next
    INDEX
    Explanations

    head

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    满
    -0.09
    ä¼Ļä¼´åħ³ç³»
    -0.08
    èĥ½èĢĹ
    -0.08
    åľ°ä¸Ĭ
    -0.08
    Ñģид
    -0.08
    ä¼IJ
    -0.08
    екÑģ
    -0.08
    geb
    -0.08
    ardi
    -0.08
    ÙĤÙģ
    -0.08
    POSITIVE LOGITS
    /head
    0.16
    é¢ħ
    0.15
     Heads
    0.15
    (head
    0.14
    -head
    0.13
    .Head
    0.13
    head
    0.13
     Head
    0.13
    =head
    0.13
     heads
    0.13
    Activations Density 0.122%

    No Known Activations