© 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. 48227
    Prev
    Next
    INDEX
    Explanations

    closing quotation marks

    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
    ened
    -0.11
    ç¿Ģ
    -0.10
    éľĦ
    -0.10
    åį¯
    -0.10
    åħĴ
    -0.09
    森æŀĹåħ¬åĽŃ
    -0.09
    åijĢ
    -0.09
    quis
    -0.09
    roke
    -0.08
    _stamp
    -0.08
    POSITIVE LOGITS
    ahn
    0.10
    Ĥæķ°
    0.09
    tte
    0.09
    ãģ¹ãģį
    0.09
    oden
    0.09
    issant
    0.09
    gable
    0.09
    ISTA
    0.09
    isma
    0.08
    maid
    0.08
    Activations Density 0.108%

    No Known Activations