© 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. 56361
    Prev
    Next
    INDEX
    Explanations

    first 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
    ierge
    -0.10
    第ä¸ĢæŶéĹ´
    -0.09
    çįŃ
    -0.09
    åıijå±ķä¸Ń
    -0.08
    .listeners
    -0.08
    ä¸Ģä¸ĸ
    -0.08
    imers
    -0.08
    кол
    -0.08
     Vac
    -0.08
    vac
    -0.08
    POSITIVE LOGITS
    /root
    0.08
    åĵªæĢķæĺ¯
    0.08
    -ever
    0.08
    åĸĦæĦı
    0.08
    appropri
    0.08
    ulo
    0.08
    æŃ£å¼ı
    0.08
    arya
    0.08
    æķ´æķ´
    0.08
    çĽĶ
    0.08
    Activations Density 0.070%

    No Known Activations