© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19583
    Prev
    Next
    INDEX
    Explanations

    Published date

    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
     pit
    -0.09
    人åĿĩ
    -0.09
    ä¸įåĪ°
    -0.09
    å©Ĩå©Ĩ
    -0.09
    otomy
    -0.09
    pane
    -0.09
    æīĵåĮħ
    -0.08
    ÑĢин
    -0.08
     gul
    -0.08
    usc
    -0.08
    POSITIVE LOGITS
    ings
    0.10
    è§ģ解
    0.09
    /lic
    0.09
    éĻħ
    0.08
    ICATION
    0.08
    عÙĦاÙħ
    0.08
    æ¡£
    0.08
    (crate
    0.08
    è°ħ解
    0.08
    addy
    0.08
    Activations Density 0.067%

    No Known Activations