© 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. 55968
    Prev
    Next
    INDEX
    Explanations

    crop factor, ISO, aperture, frames

    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
    ĵį
    -0.10
    åĥļ
    -0.09
    éŁ¿
    -0.09
    èĬ±äºĨ
    -0.08
    æµĭç»ĺ
    -0.08
    éĹŃ
    -0.08
    å¹²äºĭ
    -0.08
    ðĿijĶ
    -0.08
    -_
    -0.08
     penet
    -0.08
    POSITIVE LOGITS
    éĻµ
    0.10
    loo
    0.10
    è¯Ŀ说
    0.09
    ARAM
    0.08
     juris
    0.08
    éĵĻ
    0.08
    ä½ľæĸĩ
    0.08
    ema
    0.08
    åķĸ
    0.08
    eref
    0.08
    Activations Density 0.065%

    No Known Activations