© 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. 53515
    Prev
    Next
    INDEX
    Explanations

    expression and art

    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
    onga
    -0.09
    пÑĢÑı
    -0.08
     remot
    -0.08
     mantra
    -0.08
    .fe
    -0.08
     Meredith
    -0.08
     ri
    -0.08
    Actor
    -0.08
    лиз
    -0.07
    reu
    -0.07
    POSITIVE LOGITS
    表达
    0.15
     Expression
    0.12
     expression
    0.12
    expression
    0.10
    表达äºĨ
    0.10
    åĪĽä½ľ
    0.10
    èīºæľ¯å®¶
    0.10
     artistic
    0.10
    èīºæľ¯
    0.10
    -expression
    0.10
    Activations Density 0.080%

    No Known Activations