© 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. 61577
    Prev
    Next
    INDEX
    Explanations

    televised events

    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
     chó
    -0.09
    å¿ł
    -0.09
    åħ¬åħ±åľºæīĢ
    -0.09
    åĦŁ
    -0.09
    bib
    -0.08
    çĿ¹
    -0.08
    豪éŨ
    -0.08
    å°Ŀ
    -0.08
    è¶ĬæĿ¥è¶Ĭ
    -0.08
    æĮ¤
    -0.08
    POSITIVE LOGITS
    èľľ
    0.10
    åĪĴç®Ĺ
    0.09
    åĪ°è´¦
    0.09
    ffect
    0.08
    ordes
    0.08
    اء
    0.08
    igram
    0.08
    agn
    0.08
    åı¯è§Ĥ
    0.08
    peat
    0.08
    Activations Density 0.017%

    No Known Activations