© 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. 61644
    Prev
    Next
    INDEX
    Explanations

    search traffic

    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
     exc
    -0.09
    us
    -0.08
    è´´
    -0.08
    ç´§åĩij
    -0.08
    åįĵ
    -0.08
    5
    -0.08
    è´¬
    -0.08
    _ROUT
    -0.08
    irit
    -0.07
    elope
    -0.07
    POSITIVE LOGITS
    æľĢåIJİä¸Ģ
    0.10
    鼶ç¢İ
    0.10
    ä¸įåĪ©äºİ
    0.10
    飽
    0.10
    æīŃ
    0.09
    èħ°éĥ¨
    0.09
    课é¢ĺ
    0.09
    fil
    0.09
    åīįéĢĶ
    0.09
    melon
    0.09
    Activations Density 0.050%

    No Known Activations