© 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. 39436
    Prev
    Next
    INDEX
    Explanations

    jumping and jumping actions

    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
    оваÑĢ
    -0.10
    åĵį
    -0.10
    æijĨ
    -0.09
    èĭŀ
    -0.09
    à¸ļำ
    -0.09
    éģ¥è¿ľ
    -0.08
    çīĮåŃIJ
    -0.08
     знак
    -0.08
    adge
    -0.08
    é²Ľ
    -0.08
    POSITIVE LOGITS
    蹬
    0.13
    è¹²
    0.13
    ç«Ļç«ĭ
    0.12
    踮
    0.12
    蹦
    0.12
    åıĮèĦļ
    0.11
    å¥Ķè·ij
    0.11
    起身
    0.11
    è·³è·ĥ
    0.11
    趴
    0.10
    Activations Density 0.060%

    No Known Activations