© 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. 62012
    Prev
    Next
    INDEX
    Explanations

    candy and candy related contexts

    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
    edor
    -0.11
    è¹ij
    -0.11
    abouts
    -0.10
    sWith
    -0.10
    odore
    -0.09
    uments
    -0.09
    壮è§Ĥ
    -0.09
    eing
    -0.09
    -ext
    -0.09
    nings
    -0.08
    POSITIVE LOGITS
    çķĮçļĦ
    0.10
    ous
    0.09
    æ§Į
    0.09
    æ³ī
    0.09
    /OR
    0.09
    sticks
    0.08
    ðŁį¬
    0.08
    éro
    0.08
    ieri
    0.08
    èĪ¸
    0.08
    Activations Density 0.003%

    No Known Activations