© 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. 5155
    Prev
    Next
    INDEX
    Explanations

    disclosure of information

    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
    _TARGET
    -0.10
    icut
    -0.09
    icans
    -0.09
     Sco
    -0.09
    饱
    -0.08
    紧紧
    -0.08
    serter
    -0.08
     ÑĢавно
    -0.08
    IPH
    -0.08
    /operator
    -0.08
    POSITIVE LOGITS
    çĶ³æĬ¥
    0.17
    æĬ«éľ²
    0.11
    çĻ»è®°
    0.11
     declaration
    0.11
    çĶ³
    0.11
    åĿ¦
    0.10
     disclosure
    0.10
    åħ¬ç¤º
    0.10
     disclose
    0.10
     declare
    0.10
    Activations Density 0.070%

    No Known Activations