© 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. 33097
    Prev
    Next
    INDEX
    Explanations

    metallic hydrogen

    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
    峡
    -0.12
    _Framework
    -0.11
    ATYPE
    -0.11
    å³
    -0.11
    好æĦŁ
    -0.11
    屿
    -0.10
    涣
    -0.10
    éªĭ
    -0.10
    ä¼ģä¸ļ家
    -0.10
    rud
    -0.10
    POSITIVE LOGITS
    è¿ģ移
    0.09
    itan
    0.08
    æĹ©æľŁ
    0.08
    梯
    0.08
    rix
    0.08
     lod
    0.08
     Briggs
    0.08
    åħ¬æ°ij
    0.08
    æµ·æ°´
    0.08
    пал
    0.08
    Activations Density 0.063%

    No Known Activations