© 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. 3634
    Prev
    Next
    INDEX
    Explanations

    union or activism

    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
    .Ptr
    -0.11
    èijŃ
    -0.10
    åĽĽæĸ¹
    -0.10
    çķĻå®Ī
    -0.10
     Quad
    -0.09
    iez
    -0.09
    Quad
    -0.09
    Äı
    -0.09
    Operand
    -0.09
    ä¸įæĺĵ
    -0.09
    POSITIVE LOGITS
    æݨ
    0.11
    çĻ»
    0.09
     McCart
    0.09
    lian
    0.08
    人æµģ
    0.08
    èĢģå¹´
    0.08
     push
    0.08
    _PRI
    0.08
    æ¶Į
    0.08
    scp
    0.08
    Activations Density 0.101%

    No Known Activations