© 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. 5132
    Prev
    Next
    INDEX
    Explanations

    attenhall

    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
    sWith
    -0.20
    swith
    -0.15
    son
    -0.14
    side
    -0.13
    sh
    -0.13
    sp
    -0.13
    sm
    -0.12
    slash
    -0.12
    service
    -0.12
    screen
    -0.11
    POSITIVE LOGITS
    eker
    0.12
    heimer
    0.11
    ëģĶ
    0.11
    kind
    0.10
    ep
    0.10
    esting
    0.10
    æĸ¯åĿ¦
    0.10
     dolayı
    0.10
    vironment
    0.10
    inning
    0.10
    Activations Density 0.244%

    No Known Activations