© 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. 53851
    Prev
    Next
    INDEX
    Explanations

    information retrieval search

    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
    æ¸į
    -0.11
    俸
    -0.11
    REFIX
    -0.10
    .circular
    -0.10
    çŁ
    -0.10
    oky
    -0.10
    大æ´ĭ
    -0.10
    人èĦī
    -0.10
    \Bridge
    -0.10
    .gnu
    -0.10
    POSITIVE LOGITS
    boa
    0.09
    7
    0.08
    溱
    0.08
    8
    0.08
    2
    0.08
    6
    0.08
    3
    0.08
     search
    0.08
    iden
    0.08
     cit
    0.08
    Activations Density 0.146%

    No Known Activations