© 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. 53743
    Prev
    Next
    INDEX
    Explanations

    pin / pins

    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
    tt
    -0.11
    onest
    -0.11
    ividad
    -0.09
    s
    -0.09
    çģµæ°Ķ
    -0.09
    ingles
    -0.09
    oner
    -0.09
    sPid
    -0.08
    _MIX
    -0.08
    æĿ¯
    -0.08
    POSITIVE LOGITS
    è¢Ħ
    0.10
    legate
    0.10
    ä¸ŃåĽ½åĽ½éĻħ
    0.09
    kee
    0.09
    å²Ń
    0.09
    æ¤IJ
    0.09
    OLA
    0.08
    åĦ¿
    0.08
    ASN
    0.08
    -outs
    0.08
    Activations Density 0.008%

    No Known Activations