© 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. 23614
    Prev
    Next
    INDEX
    Explanations

    pom pom, POM Strategy, pommes

    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
    ened
    -0.10
    ably
    -0.10
    anced
    -0.09
    羿
    -0.09
    ound
    -0.09
    ence
    -0.09
    åIJĮæľŁ
    -0.09
     ëıĻìĭľìĹIJ
    -0.09
    nings
    -0.08
    éc
    -0.08
    POSITIVE LOGITS
    asz
    0.11
    æ¡Ķ
    0.11
    çĦ¶æĺ¯
    0.10
    estic
    0.09
    ifes
    0.09
    ãģĤãĤĮ
    0.08
    quets
    0.08
    åѦç§ij
    0.08
    eties
    0.08
    请大家
    0.08
    Activations Density 0.017%

    No Known Activations