© 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. 22398
    Prev
    Next
    INDEX
    Explanations

    animal species names

    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
    岫
    -0.10
    .dy
    -0.10
    æ¯ĭ
    -0.09
    è°ĥçIJĨ
    -0.09
     Pole
    -0.09
    ä¹łæĥ¯äºĨ
    -0.09
    åıijè´¢
    -0.09
    åł°
    -0.09
    çĪ±ç¾İ
    -0.08
    æĬ½çĥŁ
    -0.08
    POSITIVE LOGITS
    åIJ¸çº³
    0.09
    å¹ħ
    0.09
     Gould
    0.09
    éĴĿ
    0.09
    å°½
    0.09
    urus
    0.09
    åĨł
    0.09
    .mac
    0.08
    éľĢè¦ģçĶ¨åĪ°
    0.08
    çĤ³
    0.08
    Activations Density 0.208%

    No Known Activations