© 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. 23259
    Prev
    Next
    INDEX
    Explanations

    subscribe and subscription

    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
    éĢIJ
    -0.10
    uib
    -0.09
     ÑģÑĤÑĥд
    -0.09
    å·¥ä½ľä½ľé£İ
    -0.08
    éĽĩ
    -0.08
    å¸ķ
    -0.08
     Gabriel
    -0.08
    вал
    -0.08
    ваÑĤ
    -0.08
    gment
    -0.08
    POSITIVE LOGITS
    订éĺħ
    0.18
     subscribe
    0.15
     subscription
    0.14
    .Subscribe
    0.14
     subscribing
    0.14
     subscribed
    0.14
    _subscribe
    0.14
    .subscription
    0.14
     Subscription
    0.14
    subscribe
    0.13
    Activations Density 0.063%

    No Known Activations