© 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. 53416
    Prev
    Next
    INDEX
    Explanations

    localhost, Georgetown, genome

    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
    -0.14
    ç±³å°Ķ
    -0.10
    çĶ¾
    -0.09
    combe
    -0.09
    NING
    -0.09
    ught
    -0.09
    èĨĬ
    -0.09
    unar
    -0.09
    оÑģÑĤоÑı
    -0.09
    å®ģæ³¢å¸Ĥ
    -0.09
    POSITIVE LOGITS
    inker
    0.09
     же
    0.09
     Hữu
    0.08
    访
    0.08
    妲
    0.08
    Ñģко
    0.08
    ection
    0.08
    -priced
    0.08
    pto
    0.08
    .logged
    0.08
    Activations Density 0.002%

    No Known Activations