© 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. 17117
    Prev
    Next
    INDEX
    Explanations

    without limitation

    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
    ampler
    -0.09
    é¢ĨåħĪçļĦ
    -0.09
    ç»´
    -0.09
    çī¹éķ¿
    -0.09
    没è§ģè¿ĩ
    -0.09
    åħ»èĢģéĩij
    -0.08
    /or
    -0.08
    åı¤æĢª
    -0.08
    ritos
    -0.08
    oris
    -0.08
    POSITIVE LOGITS
    è´±
    0.09
    ä½ĵçİ°åľ¨
    0.09
    bih
    0.09
    ä»ĩ
    0.08
    çĶĺ
    0.08
    _codegen
    0.08
    .compress
    0.08
     Slate
    0.08
    WISE
    0.08
    еле
    0.08
    Activations Density 0.028%

    No Known Activations