© 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. 61001
    Prev
    Next
    INDEX
    Explanations

    motorcycle related words

    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
    fur
    -0.10
    ä¸İåıijå±ķ
    -0.09
    nish
    -0.09
    o
    -0.09
    otre
    -0.08
    æĻ°
    -0.08
    anka
    -0.08
    èĩªçĦ¶ç§ijåѦ
    -0.08
    ÂŃi
    -0.08
    oS
    -0.08
    POSITIVE LOGITS
    çĶ¨åĵģ
    0.10
    pedia
    0.10
    eros
    0.09
    åıijå±ķ空éĹ´
    0.09
    é¾Ħ
    0.09
    ISTS
    0.09
    éķ¿èĢģ
    0.09
    çİĭåĽ½
    0.09
    æijĶåĢĴ
    0.08
    olk
    0.08
    Activations Density 0.009%

    No Known Activations