© 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. 54206
    Prev
    Next
    INDEX
    Explanations

    environment and setting

    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
    ç®±åŃIJ
    -0.08
    æĶ¶çº³
    -0.08
    è¯
    -0.08
    esch
    -0.07
    aten
    -0.07
    è¿ijäºĽ
    -0.07
     principles
    -0.07
     outr
    -0.07
    åıijå±ķè§ĦåĪĴ
    -0.07
    atin
    -0.07
    POSITIVE LOGITS
    çݯå¢ĥä¸Ń
    0.22
    çݯå¢ĥä¸ĭ
    0.22
    çݯå¢ĥ
    0.19
     environment
    0.19
     environments
    0.18
    çĴ°å¢ĥ
    0.17
    _environment
    0.16
     Environment
    0.15
    Environment
    0.15
     envi
    0.14
    Activations Density 0.221%

    No Known Activations