© 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. 56799
    Prev
    Next
    INDEX
    Explanations

    copyright infringement

    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
    ndx
    -0.09
    sWith
    -0.09
    lessly
    -0.09
    ÙĪا
    -0.08
    west
    -0.08
    oret
    -0.08
    olla
    -0.08
    vil
    -0.08
    åĢ¦
    -0.08
    altung
    -0.08
    POSITIVE LOGITS
     incor
    0.09
    äºĨæĪijçļĦ
    0.09
     Nap
    0.09
    urus
    0.09
    avra
    0.09
    ç©°
    0.09
    ä¸ĵç§ij
    0.09
    åĨ°æ·ĩæ·ĭ
    0.09
    avar
    0.08
    è¡į
    0.08
    Activations Density 0.002%

    No Known Activations