© 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. 2489
    Prev
    Next
    INDEX
    Explanations

    license identifiers

    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
    ÑĤик
    -0.11
    Scheduled
    -0.10
    vale
    -0.09
    ÑĢÑĥÑĤ
    -0.09
    OTP
    -0.09
    Õ²
    -0.09
    å¼ĢæĪ·
    -0.09
    è£ħå¤ĩåĪ¶éĢł
    -0.09
    ðŁĵĺ
    -0.09
    ressing
    -0.09
    POSITIVE LOGITS
     license
    0.13
     License
    0.12
    License
    0.10
    license
    0.10
     licence
    0.10
    许åı¯
    0.10
     LICENSE
    0.10
    /LICENSE
    0.09
     licenses
    0.09
    -License
    0.09
    Activations Density 0.786%

    No Known Activations