© 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. 35008
    Prev
    Next
    INDEX
    Explanations

    remote tracking and location

    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
    _DOCUMENT
    -0.09
    颦
    -0.09
    åŃª
    -0.09
    ILA
    -0.09
    æĤ²åĵĢ
    -0.09
    gon
    -0.09
    æĥĬ人
    -0.09
    strup
    -0.09
    å§ij
    -0.09
    FileStream
    -0.09
    POSITIVE LOGITS
    åıij声
    0.10
    å£°éŁ³
    0.10
    溯
    0.09
    æŃ£çīĪ
    0.08
    åİĭåĪ¶
    0.08
    ä¿¡æģ¯åıijå¸ĥ
    0.08
    ç«
    0.08
    èģ²éŁ³
    0.08
    夹
    0.08
    声åĵį
    0.08
    Activations Density 0.125%

    No Known Activations