© 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. 51049
    Prev
    Next
    INDEX
    Explanations

    crazy

    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
    èĻ±
    -0.10
    æĪij对
    -0.09
    astr
    -0.08
    ÑĢажа
    -0.08
    auer
    -0.08
    reira
    -0.08
    stri
    -0.08
    çĦ¶æĺ¯
    -0.08
    uce
    -0.08
     ÑĩеÑĢ
    -0.08
    POSITIVE LOGITS
    fully
    0.13
     havoc
    0.12
    iness
    0.11
    0.10
    ¶
    0.10
    appa
    0.09
    liest
    0.09
    iggers
    0.09
    engers
    0.09
    oney
    0.09
    Activations Density 0.007%

    No Known Activations