© 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. 17708
    Prev
    Next
    INDEX
    Explanations

    Saratoga, Annapolis, Peoria, Boulevard

    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
    eger
    -0.10
    zel
    -0.08
    è´¢
    -0.08
    GMT
    -0.08
    jec
    -0.08
    tc
    -0.08
    禽
    -0.07
    opc
    -0.07
    uder
    -0.07
    acket
    -0.07
    POSITIVE LOGITS
    itra
    0.12
    ullo
    0.11
    æĭ¿çĿĢ
    0.10
    çĴĭ
    0.10
    åĥ¦
    0.10
    踮
    0.10
    éĢĢ
    0.10
    ä¸įä¸ĭ
    0.10
    äºĭä¸ļåıijå±ķ
    0.09
    æĭ¿äºĨ
    0.09
    Activations Density 0.003%

    No Known Activations