© 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. 53665
    Prev
    Next
    INDEX
    Explanations

    license text

    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
    æ±
    -0.10
    çĥĺçĦĻ
    -0.09
    åIJĥè¿ĩ
    -0.08
     Unused
    -0.08
    èµŃ
    -0.08
    ä¿¡çĶ¨
    -0.08
    çĶ³è¯ī
    -0.08
    绿水
    -0.08
    3
    -0.08
     vs
    -0.08
    POSITIVE LOGITS
    ãĤ«ãĥ³
    0.11
    yne
    0.10
    éĻ¤æѤ
    0.09
    otron
    0.09
    .Dial
    0.09
    atz
    0.09
    -regexp
    0.09
    tol
    0.09
    enal
    0.09
    ilion
    0.09
    Activations Density 0.178%

    No Known Activations