© 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. 38419
    Prev
    Next
    INDEX
    Explanations

    value of

    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
    altitude
    -0.10
    èĥļ
    -0.09
    arak
    -0.09
     оÑĩеÑĢ
    -0.09
    æĪij们ä¸Ģèµ·
    -0.09
    å¤ĸåľ°
    -0.09
    éĵ°
    -0.09
    çł´æįŁ
    -0.09
    reak
    -0.09
    迹
    -0.08
    POSITIVE LOGITS
    -added
    0.13
    -nil
    0.11
    uetype
    0.09
    ninger
    0.09
    åĭĴ
    0.09
    uess
    0.09
    uet
    0.08
    uing
    0.08
    åĭ¤
    0.08
    éĻªä¼´
    0.08
    Activations Density 0.223%

    No Known Activations