© 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. 54287
    Prev
    Next
    INDEX
    Explanations

    chris plus name or name suffix

    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
    ะ
    -0.12
     лиÑĪÑĮ
    -0.10
    é³Ħ
    -0.09
    erah
    -0.09
    iert
    -0.09
    大湾åĮº
    -0.09
    /problems
    -0.08
    -0.08
    ação
    -0.08
    rio
    -0.08
    POSITIVE LOGITS
    opher
    0.12
    mania
    0.11
    acter
    0.11
    aceous
    0.11
    otle
    0.10
    ophe
    0.10
    avel
    0.09
    ses
    0.09
    IBUT
    0.09
    íĥĪ
    0.09
    Activations Density 0.030%

    No Known Activations