© 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. 23102
    Prev
    Next
    INDEX
    Explanations

    it directly or through

    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
    ãng
    -0.09
    è´µ
    -0.09
     OK
    -0.08
    éĩįå¿ĥ
    -0.08
    棣
    -0.07
    rite
    -0.07
    è°Ĺ
    -0.07
    Reply
    -0.07
    ãģĭãģijãģ¦
    -0.07
    èļ©
    -0.07
    POSITIVE LOGITS
    人们对
    0.10
    ãĤ¨ãĥįãĥ«
    0.09
    è°¤
    0.09
    istik
    0.09
    çĽĬ
    0.09
    hores
    0.09
    éļĺ
    0.09
    æ½®
    0.09
    çªľ
    0.09
    _Function
    0.09
    Activations Density 0.085%

    No Known Activations