© 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. 4966
    Prev
    Next
    INDEX
    Explanations

    regarding copyright

    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
    /or
    -0.13
    éri
    -0.09
     знаÑĩиÑĤ
    -0.09
    å½ĵåį³
    -0.09
     Jae
    -0.09
    å¤ł
    -0.09
    무
    -0.09
    æŃ£åĽłä¸º
    -0.09
    å¤Ł
    -0.09
    erus
    -0.09
    POSITIVE LOGITS
    æѤäºĭ
    0.11
    forth
    0.10
    åIJĦç§į
    0.09
    ably
    0.09
    afen
    0.09
    offer
    0.09
     моÑīн
    0.09
    ult
    0.08
    ately
    0.08
    acht
    0.08
    Activations Density 0.012%

    No Known Activations