© 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. 58136
    Prev
    Next
    INDEX
    Explanations

    combination of options

    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
    åĬŀäºĭ
    -0.10
    .mapbox
    -0.09
    IFORM
    -0.09
    SplitOptions
    -0.09
    _Parms
    -0.09
    è²Į
    -0.09
     \@
    -0.09
    çĶ¨æĪ·æıIJä¾Ľ
    -0.09
     fools
    -0.09
    è¿Ļ件äºĭ
    -0.09
    POSITIVE LOGITS
    ç»ĦåIJĪ
    0.10
    annon
    0.08
    å¼Ľ
    0.08
     combinations
    0.08
    éģ´éĢī
    0.08
    lander
    0.08
    æľĽåİ»
    0.08
    patch
    0.08
    èĬ
    0.08
    anoia
    0.08
    Activations Density 0.024%

    No Known Activations