© 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. 27542
    Prev
    Next
    INDEX
    Explanations

    King followed by specific words

    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
    ROTO
    -0.10
    ists
    -0.10
    oses
    -0.09
    ting
    -0.09
    fgang
    -0.09
    ç§ī
    -0.09
    TERS
    -0.08
    ÑĢак
    -0.08
    IAS
    -0.08
    ãģĦãģĨ
    -0.08
    POSITIVE LOGITS
    ston
    0.12
    pin
    0.11
    don
    0.10
    lake
    0.10
    éĻĽ
    0.09
    liness
    0.09
    pes
    0.09
    redients
    0.09
    dom
    0.09
    ÑģпоÑĢ
    0.08
    Activations Density 0.028%

    No Known Activations