© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20829
    Prev
    Next
    INDEX
    Explanations

    number of

    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
    ðŁı»
    -0.14
    rô
    -0.10
    Ĥæķ°
    -0.10
    หมายà¹Ģลà¸Ĥ
    -0.09
    ¶
    -0.09
    ðŁı¼
    -0.09
    ures
    -0.09
    rop
    -0.09
    ensible
    -0.08
    姥
    -0.08
    POSITIVE LOGITS
    istic
    0.10
    oft
    0.10
    å§Ķåī¯ä¹¦è®°
    0.10
    çIJĨæĥ³çļĦ
    0.09
    .parseFloat
    0.09
     ÑĤелеÑĦ
    0.09
    æĻĤåĢĻ
    0.09
    ised
    0.09
    íĮIJ
    0.09
    hood
    0.08
    Activations Density 0.079%

    No Known Activations