© 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. 63263
    Prev
    Next
    INDEX
    Explanations

    illumination and light

    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
    opot
    -0.10
    orio
    -0.10
    å·´å·´
    -0.09
    moz
    -0.09
    ullet
    -0.09
    妥
    -0.08
    agger
    -0.08
    åľ°å¤Ħ
    -0.08
    mint
    -0.08
    AGO
    -0.08
    POSITIVE LOGITS
    å½»
    0.11
    eldon
    0.10
    审议
    0.09
    大米
    0.08
    suit
    0.08
    çĬģ
    0.08
    letic
    0.08
    çģ¿çĥĤ
    0.08
    affle
    0.08
    çĥģ
    0.08
    Activations Density 0.040%

    No Known Activations