© 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. 54282
    Prev
    Next
    INDEX
    Explanations

    suave, suitor, sudo, support

    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
    ãģ¾ãģ¾
    -0.12
    æ¶ķ
    -0.10
    /videos
    -0.09
    å±İ
    -0.09
    sWith
    -0.09
    æĥ®
    -0.08
    sel
    -0.08
    ssid
    -0.08
    äºĨ个
    -0.08
    ss
    -0.08
    POSITIVE LOGITS
    ETCH
    0.12
    åīįèĢħ
    0.11
    erte
    0.10
    èĩ¾
    0.10
    CEED
    0.10
    eldo
    0.10
    å¾Īå¤ļ
    0.09
    cede
    0.09
    nder
    0.09
    -called
    0.09
    Activations Density 0.022%

    No Known Activations