© 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. 2935
    Prev
    Next
    INDEX
    Explanations

    Jamaican people and places

    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
    æĶ¹éĢł
    -0.10
    erner
    -0.10
    rimp
    -0.10
    åĬĽæ±Ĥ
    -0.10
    ewe
    -0.10
    acic
    -0.09
    parity
    -0.09
    .gnu
    -0.09
    riba
    -0.09
    ë¹Ħìļ©
    -0.09
    POSITIVE LOGITS
     Rounds
    0.08
    ãĥ²
    0.08
    2
    0.08
    4
    0.08
    ç§Ń
    0.08
    1
    0.08
     Unauthorized
    0.08
    8
    0.08
     Moff
    0.07
    æĭĽå¾ħ
    0.07
    Activations Density 0.004%

    No Known Activations