© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9992
    Prev
    Next
    INDEX
    Explanations

    auto followed by word

    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
    çĽ¾
    -0.09
    iske
    -0.09
    /renderer
    -0.09
    éIJĺ
    -0.09
    еÑĨ
    -0.09
    WithOptions
    -0.09
    abox
    -0.09
    acle
    -0.09
    严èĤĥ
    -0.08
    .EMPTY
    -0.08
    POSITIVE LOGITS
    immune
    0.09
    aves
    0.09
    æĹģ
    0.08
    çķĮçļĦ
    0.08
     ка
    0.08
    äºĶè¡Į
    0.08
    è¦ĥ
    0.08
    è£ħ
    0.08
    amp
    0.08
    obby
    0.08
    Activations Density 0.014%

    No Known Activations