© 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. 23298
    Prev
    Next
    INDEX
    Explanations

    squirrels

    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
    人æ°Ķ
    -0.12
    ãĥ³ãĤ°
    -0.10
    ocking
    -0.10
    ×Ļ×Ķ
    -0.10
    IMUM
    -0.09
    è´¨éĩıåĴĮ
    -0.09
    çijŃ
    -0.09
    rray
    -0.09
    æī«é»ij
    -0.09
    褥
    -0.09
    POSITIVE LOGITS
    ness
    0.10
    鹿
    0.09
    butt
    0.08
    åĩºåİ»
    0.08
    ly
    0.08
    onto
    0.08
    ambi
    0.08
    ships
    0.08
    rd
    0.08
    appa
    0.08
    Activations Density 0.004%

    No Known Activations