© 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. 28148
    Prev
    Next
    INDEX
    Explanations

    directly proportional to

    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
    оÑĤоÑĢ
    -0.08
    _Context
    -0.08
    æī¿
    -0.08
     widow
    -0.08
    NaN
    -0.08
    æĬľ
    -0.08
    è¿Ļé¦ĸ
    -0.08
     bible
    -0.08
     carefully
    -0.08
    夹
    -0.08
    POSITIVE LOGITS
    åħ³ç³»
    0.12
     invers
    0.11
    çļĦåħ³ç³»
    0.10
    éĢ®
    0.10
     relationship
    0.10
    ä¸įæĪIJ
    0.09
    -inverse
    0.09
    éĺĴ
    0.09
    éĹľä¿Ĥ
    0.09
    ENCY
    0.09
    Activations Density 0.352%

    No Known Activations