© 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. 10747
    Prev
    Next
    INDEX
    Explanations

    iHeartMedia

    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
     Ñģобой
    -0.10
    èĥĮåĮħ
    -0.09
    æ·±æĥħ
    -0.09
    baz
    -0.09
    åı¨
    -0.09
    crit
    -0.08
    åķĨåĬ¡éĥ¨
    -0.08
    _trap
    -0.08
    ATER
    -0.08
     Ñģк
    -0.08
    POSITIVE LOGITS
    æ¯ķ
    0.10
    æĶ¹åıĺäºĨ
    0.09
    openh
    0.09
    ivism
    0.08
    obar
    0.08
    åħ¼
    0.08
    наÑĤ
    0.08
    å¾Ģå¹´
    0.08
    orus
    0.08
    ariat
    0.08
    Activations Density 0.004%

    No Known Activations