© 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. 56873
    Prev
    Next
    INDEX
    Explanations

    distress

    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
    quiv
    -0.10
    orial
    -0.09
    ization
    -0.09
    tering
    -0.09
    æīĵå¾Ĺ
    -0.08
    åĪĩå®ŀ
    -0.08
    è¿Ļæł·è¯´
    -0.08
    æŀ¶åŃIJ
    -0.08
    nect
    -0.08
    åĦ¿
    -0.08
    POSITIVE LOGITS
    ingly
    0.15
    ively
    0.10
    -metadata
    0.10
     Lage
    0.10
    ä¸Ģéĺµ
    0.09
    æįİ
    0.09
    ses
    0.09
    å¿¡
    0.09
    amel
    0.09
    ently
    0.09
    Activations Density 0.006%

    No Known Activations