© 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. 38500
    Prev
    Next
    INDEX
    Explanations

    a or an followed by a noun

    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
    (cond
    -0.08
     familiar
    -0.08
    çĨŁ
    -0.08
     reg
    -0.08
    Disp
    -0.08
     Pros
    -0.07
     Gent
    -0.07
     able
    -0.07
    AREN
    -0.07
    æ±²åıĸ
    -0.07
    POSITIVE LOGITS
    æĵ¾
    0.12
    æī°
    0.11
    ?page
    0.10
    zte
    0.10
    åħĢ
    0.10
    åıijçĶŁåľ¨
    0.10
    ichel
    0.10
    eron
    0.10
    çļĦ羣å®ŀ
    0.09
    ÑĤÑĢо
    0.09
    Activations Density 0.009%

    No Known Activations