© 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. 17346
    Prev
    Next
    INDEX
    Explanations

    a/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
    ary
    -0.08
    æĢ§çĸ¾çĹħ
    -0.08
    缸åħ³è§Ħå®ļ
    -0.08
    èĢĮä¸įæĺ¯
    -0.08
    çĤ¹æ»´
    -0.08
     rather
    -0.08
    renom
    -0.08
    RLF
    -0.08
    趣åij³
    -0.08
    IRA
    -0.08
    POSITIVE LOGITS
    èĩ³äºİ
    0.11
    zelf
    0.10
    /from
    0.09
     proport
    0.09
    ë°
    0.09
    RIC
    0.09
    åĪĽ
    0.09
    -grand
    0.09
    roup
    0.09
    çĪĨ
    0.09
    Activations Density 0.009%

    No Known Activations