© 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. 17652
    Prev
    Next
    INDEX
    Explanations

    games and sports activities

    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
    æĥ°
    -0.09
    裸
    -0.09
    å¾Īæ¼Ĥ亮
    -0.09
    íķij
    -0.08
    æĭĹ
    -0.08
    rite
    -0.08
    èĶ«
    -0.08
    ienes
    -0.08
    æľĢç¾İçļĦ
    -0.08
    cola
    -0.08
    POSITIVE LOGITS
    çĮ·
    0.09
    optional
    0.09
    èķ²
    0.09
    被æ·ĺæ±°
    0.08
    è°Ķ
    0.08
    transpose
    0.08
    å¼¹æĢ§
    0.08
     оÑĤно
    0.08
    CKER
    0.08
    /pm
    0.08
    Activations Density 0.017%

    No Known Activations