© 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. 37530
    Prev
    Next
    INDEX
    Explanations

    mistakenly destroys existence 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
    çļĦæĥħ绪
    -0.08
    ä»ħä¾Ľ
    -0.08
    çľģåĨħ
    -0.08
    2
    -0.08
    åħ¬ç½ijå®īå¤ĩ
    -0.08
    ç»ŃèĪª
    -0.08
    çļĦä¸Ģéĥ¨åĪĨ
    -0.08
    è§ģæķĪ
    -0.08
    容纳
    -0.08
    纶
    -0.07
    POSITIVE LOGITS
    ribly
    0.09
    (EXPR
    0.09
    礼æĭľ
    0.09
    chsel
    0.09
    ༺
    0.09
    leck
    0.09
    زÙĪ
    0.09
    .Iter
    0.09
    èħ´
    0.08
    _FORWARD
    0.08
    Activations Density 0.334%

    No Known Activations