© 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. 58816
    Prev
    Next
    INDEX
    Explanations

    external followed by links or services

    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
    èĶ¼
    -0.10
    INAL
    -0.09
    说æĺ¯
    -0.09
    /her
    -0.09
    _EXPRESSION
    -0.08
    lobal
    -0.08
    ician
    -0.08
    è°©
    -0.08
    èݪ
    -0.08
    çĬĢ
    -0.08
    POSITIVE LOGITS
    涯
    0.12
    -facing
    0.12
    ordinary
    0.11
    ities
    0.11
    /disable
    0.11
    encion
    0.11
    ponents
    0.10
    most
    0.10
    /Internal
    0.10
    лÑij
    0.10
    Activations Density 0.025%

    No Known Activations