© 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. 18196
    Prev
    Next
    INDEX
    Explanations

    contact us or help

    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
    æĹ¶å¸¸
    -0.09
    认æ¸ħ
    -0.08
     already
    -0.08
    orque
    -0.07
    áo
    -0.07
     ult
    -0.07
    andi
    -0.07
     Santa
    -0.07
    iring
    -0.07
     Bundy
    -0.07
    POSITIVE LOGITS
    ä¸įè´Ł
    0.12
    ä¸ºä½ł
    0.11
    åĽŀé¦Ī
    0.11
    没éĹ®é¢ĺ
    0.10
    urtle
    0.10
    注æĺİåĩºå¤Ħ
    0.09
    éĴĪ对æĢ§
    0.09
    äºĪ以
    0.09
    å¸®ä½ł
    0.09
     Äijáp
    0.09
    Activations Density 0.039%

    No Known Activations