© 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. 31222
    Prev
    Next
    INDEX
    Explanations

    level

    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
    å¯¹æľªæĿ¥
    -0.09
    åij³éģĵ
    -0.08
    寿
    -0.08
     Nico
    -0.08
    èµĶ
    -0.08
    riv
    -0.08
     Nam
    -0.08
    ä¸Ģç§Ĵ
    -0.08
    ä¸įç®Ĺ
    -0.08
    Own
    -0.08
    POSITIVE LOGITS
    level
    0.14
     level
    0.13
    -level
    0.13
     ÑĥÑĢовне
    0.12
     nivel
    0.12
    -Level
    0.12
     nÃŃvel
    0.12
    ãĥ¬ãĥĻãĥ«
    0.12
     düzey
    0.12
    .level
    0.11
    Activations Density 0.092%

    No Known Activations