© 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. 1268
    Prev
    Next
    INDEX
    Explanations

    resurrected, resuscitation, revive

    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
    ungi
    -0.10
    ince
    -0.09
    ActivityResult
    -0.09
    aille
    -0.09
    UNC
    -0.09
    MouseDown
    -0.09
    licity
    -0.08
    ä¸Ģå¤ľ
    -0.08
    ippo
    -0.08
    å®Įæķ´æĢ§
    -0.08
    POSITIVE LOGITS
    纥
    0.09
    åĴĮå®ĮåĸĦ
    0.09
    ively
    0.09
    coal
    0.09
    ä¸İåıijå±ķ
    0.09
    -ev
    0.09
    reb
    0.09
    çıij
    0.09
    第ä¸Ģä½į
    0.09
    ÃĩÃĥO
    0.09
    Activations Density 0.009%

    No Known Activations