© 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. 22219
    Prev
    Next
    INDEX
    Explanations

    special unicode characters

    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
    å·²ä¹ħçļĦ
    -0.11
    nement
    -0.11
    ÑģÑĤвоваÑĤÑĮ
    -0.08
    riad
    -0.08
    èĩĥ
    -0.08
    iffe
    -0.08
    ughter
    -0.08
    rush
    -0.08
    cest
    -0.08
    åľ¬
    -0.07
    POSITIVE LOGITS
    çĦ¶æĺ¯
    0.14
    amp
    0.10
    rain
    0.09
    sl
    0.08
    é¦ĸ缸
    0.08
    iner
    0.08
    Ñĥб
    0.08
    atively
    0.08
     flo
    0.08
    rah
    0.07
    Activations Density 0.475%

    No Known Activations