© 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. 1929
    Prev
    Next
    INDEX
    Explanations

    Association

    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
    é£ŀæī¬
    -0.09
    åIJ
    -0.09
    åħį
    -0.09
    èĢģ人家
    -0.09
    bear
    -0.08
    åĿļå®ļä¸į
    -0.08
    侧ç»ĵæŀĦæĢ§
    -0.08
    æĿĤå¿Ĺ社
    -0.08
    åİ¿åħ¬å®īå±Ģ
    -0.08
    bread
    -0.08
    POSITIVE LOGITS
    гÑĥ
    0.10
    ught
    0.10
    ero
    0.09
    弩
    0.09
    (SIG
    0.09
    ãĤĮãģ°
    0.09
    ONTAL
    0.08
    иÑĤелÑĮн
    0.08
    ampo
    0.08
    ÊĬ
    0.08
    Activations Density 0.017%

    No Known Activations