© 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. 11488
    Prev
    Next
    INDEX
    Explanations

    theria, Asia, term, .html

    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
    çĤ¹è¯Ħ
    -0.10
    å¹²èĦĨ
    -0.10
    udd
    -0.09
    hart
    -0.09
    åĢĴ
    -0.09
    èIJ¥
    -0.09
    ipo
    -0.09
    çĩŁ
    -0.09
    ç²Ĺ
    -0.09
    StringBuilder
    -0.08
    POSITIVE LOGITS
    缮
    0.10
    è¿ĻæĶ¯
    0.10
    触åıĬ
    0.10
    ieved
    0.09
    å¿Į
    0.09
    uset
    0.09
    宣
    0.08
    ноÑģÑĤ
    0.08
    ноп
    0.08
    touches
    0.08
    Activations Density 0.036%

    No Known Activations