© 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. 51145
    Prev
    Next
    INDEX
    Explanations

    reopening, reopening, reinstall, reconnect

    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
    bread
    -0.10
    à¸Ĭะ
    -0.10
    GRAM
    -0.10
    adel
    -0.09
    stick
    -0.09
    åĮĸçļĦ
    -0.09
    lore
    -0.09
    stone
    -0.09
    raj
    -0.09
    ized
    -0.09
    POSITIVE LOGITS
    äºĨä¸Ģéģį
    0.13
    ä¸Ģéģį
    0.11
    åĴĮå®ĮåĸĦ
    0.11
    wards
    0.10
    entrant
    0.10
    ÑĤÑĥ
    0.10
    æŃĩ
    0.09
    ento
    0.09
    åİī
    0.09
    审è§Ĩ
    0.09
    Activations Density 0.120%

    No Known Activations