© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6836
    Prev
    Next
    INDEX
    Explanations

    inhabited / inhabitants

    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
    dish
    -0.11
    ifiable
    -0.10
    骥
    -0.10
    ìį¨
    -0.09
    IFY
    -0.09
    pec
    -0.09
    arith
    -0.09
    ebra
    -0.09
    ÅŁt
    -0.09
    .lift
    -0.09
    POSITIVE LOGITS
    å·¢
    0.10
    ãĤĤãģĨ
    0.10
    rary
    0.09
    人éĥ½
    0.09
    agi
    0.09
    èĢħçļĦ
    0.09
    /support
    0.08
    zá
    0.08
    erval
    0.08
    ../../../
    0.08
    Activations Density 0.014%

    No Known Activations