© 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. 33224
    Prev
    Next
    INDEX
    Explanations

    people interested in something

    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
    æĦŁ
    -0.10
    é£İåı£
    -0.10
    çĺ¿
    -0.10
    èµ°åĬ¿
    -0.09
    æį¢å±Ĭ
    -0.09
    åħ¥æĪ·
    -0.09
    éĢĥ离
    -0.09
    笳
    -0.09
    é£İè²Į
    -0.09
     ÑĢаÑģÑģ
    -0.09
    POSITIVE LOGITS
    ç¿ģ
    0.10
    atics
    0.10
    appropri
    0.08
    gov
    0.08
    GMT
    0.08
    çªŁ
    0.08
    aid
    0.08
    dana
    0.08
    人家
    0.08
    enos
    0.08
    Activations Density 0.036%

    No Known Activations