© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51309
    Prev
    Next
    INDEX
    Explanations

    clam, oyster, mussels

    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
     caval
    -0.08
    etta
    -0.08
     cotton
    -0.08
    LEN
    -0.08
    uder
    -0.08
    æ¶ĤæĬ¹
    -0.08
    omal
    -0.08
    é¢ijé¢ij
    -0.07
    uzzi
    -0.07
    ces
    -0.07
    POSITIVE LOGITS
    å·²ä¹ħçļĦ
    0.11
    åļ·
    0.10
    unic
    0.10
    воÑĢ
    0.10
    auce
    0.10
    auty
    0.09
    åij±
    0.09
    åij¨åĽ´
    0.09
    urg
    0.09
    èŁĨ
    0.09
    Activations Density 0.007%

    No Known Activations