© 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. 56951
    Prev
    Next
    INDEX
    Explanations

    prepare to work

    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
    éĺ²çĽĹ
    -0.09
    æĿ¡çº¦
    -0.09
    èĹī
    -0.09
    è¿ĩçļĦ
    -0.09
    å·¥å§Ķ
    -0.09
    åĩłæ¬¡
    -0.09
    ä¾ĭå¤ĸ
    -0.09
    ç±į
    -0.08
    çľĭä»ĸ
    -0.08
    xBF
    -0.08
    POSITIVE LOGITS
    åºĶ对
    0.14
    èĥľä»»
    0.13
    ä¸Ĭå²Ĺ
    0.12
    éĿ¢å¯¹
    0.10
    åĨįåİ»
    0.10
    èĩªå¦Ĥ
    0.09
    abet
    0.09
    æĬķ身
    0.08
    æĪIJ为
    0.08
    andle
    0.08
    Activations Density 0.059%

    No Known Activations