© 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. 63019
    Prev
    Next
    INDEX
    Explanations

    evil organization, within, eyes, overlord, dead

    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
    æijĨæĶ¾
    -0.10
    ech
    -0.09
    ìĨĶ
    -0.09
    åħ¶ä»ĸ人
    -0.08
    rab
    -0.08
    å°ı康
    -0.08
    缺åı£
    -0.08
    è·Ħ
    -0.08
    пÑĥÑģÑĤ
    -0.08
    ansson
    -0.08
    POSITIVE LOGITS
    fully
    0.11
    ulous
    0.10
     intent
    0.09
    ously
    0.09
    foy
    0.09
    igor
    0.09
    -looking
    0.09
    okin
    0.09
    èĽĭ
    0.09
    éĢ¼
    0.09
    Activations Density 0.019%

    No Known Activations