© 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. 55246
    Prev
    Next
    INDEX
    Explanations

    from numerical, James, Eric, Parad

    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
    媵
    -0.10
    ç»ĵ
    -0.10
    æĹĦ
    -0.10
    åij½é¢ĺ
    -0.09
    åī¥
    -0.09
    å®Įæķ´
    -0.09
    èݳ
    -0.09
     Opr
    -0.09
    outu
    -0.09
    ParameterValue
    -0.08
    POSITIVE LOGITS
     http
    0.11
    :http
    0.10
    èĥ½å¾ĹåĪ°
    0.09
    (http
    0.09
    http
    0.09
    'http
    0.09
    .http
    0.09
    "http
    0.08
    å¾ĹåĪ°äºĨ
    0.08
    ãĢĬ
    0.08
    Activations Density 0.053%

    No Known Activations