© 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. 22549
    Prev
    Next
    INDEX
    Explanations

    positive reviews

    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
    gross
    -0.10
    थ
    -0.09
    ering
    -0.09
     Timeline
    -0.08
     rusty
    -0.08
    ä¸Ģç·Ĵãģ«
    -0.08
    ç²Ĺ
    -0.08
    ollower
    -0.08
    жи
    -0.08
    éħį
    -0.08
    POSITIVE LOGITS
    åĬ¿å¤´
    0.10
    å¥Ī
    0.10
    å·²ä¹ħ
    0.10
    èµĶ
    0.09
    endar
    0.09
    ç¼±
    0.09
    (Parcel
    0.09
    ä¼ģä¸ļåĴĮ
    0.09
    èĦijåŃIJ
    0.08
    VIN
    0.08
    Activations Density 0.024%

    No Known Activations