© 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. 57224
    Prev
    Next
    INDEX
    Explanations

    Museum Art exhibitions

    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
     cud
    -0.09
    NT
    -0.09
    nt
    -0.08
    eam
    -0.08
    kus
    -0.08
     NT
    -0.08
    æ·ĭ
    -0.08
    æĶ¹æŃ£
    -0.08
    ICES
    -0.08
    ely
    -0.08
    POSITIVE LOGITS
    æįĭ
    0.12
    ç»Ī身
    0.11
    éħĿéħ¿
    0.10
    æĦ«
    0.10
    ä¸įä¸ĭ
    0.09
    ffen
    0.09
     Tender
    0.09
    daq
    0.09
    å·§
    0.09
    çŃīéĥ¨éŨ
    0.09
    Activations Density 0.024%

    No Known Activations