© 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. 36093
    Prev
    Next
    INDEX
    Explanations

    assurance and reassurance

    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
    ugal
    -0.10
    ạm
    -0.10
    ested
    -0.09
    heimer
    -0.09
    estatus
    -0.08
    è¾ĩ
    -0.08
    -0.08
    asket
    -0.08
    æĪij们认为
    -0.08
    好ä¸į容æĺĵ
    -0.08
    POSITIVE LOGITS
    ingly
    0.13
    amel
    0.11
    åīĤ
    0.10
     rằng
    0.10
    OCI
    0.09
    ignet
    0.09
    ably
    0.09
    oron
    0.09
    è¿©
    0.09
    coe
    0.09
    Activations Density 0.008%

    No Known Activations