© 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. 18713
    Prev
    Next
    INDEX
    Explanations

    purpose

    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
    åħ³äºİæĪij们
    -0.10
    rd
    -0.09
    ç´¯äºĨ
    -0.09
    èĪ
    -0.09
    ews
    -0.09
    lords
    -0.08
    çİ°åĩº
    -0.08
    éĿĻéĿĻåľ°
    -0.08
    rob
    -0.08
    ropa
    -0.08
    POSITIVE LOGITS
    fully
    0.17
    ful
    0.16
    lessly
    0.15
    AnimationFrame
    0.12
    ately
    0.12
    FUL
    0.11
    lessness
    0.11
    OfWork
    0.11
    ively
    0.10
    -built
    0.10
    Activations Density 0.026%

    No Known Activations