© 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. 58529
    Prev
    Next
    INDEX
    Explanations

    party

    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
    lessly
    -0.10
    åĨįè§ģ
    -0.09
    atin
    -0.09
    åıijå±ķä¸Ń
    -0.09
    èļį
    -0.08
    æļ§
    -0.08
     Happiness
    -0.08
    ãĢĸ
    -0.08
    (pat
    -0.08
    é¦ĭ
    -0.08
    POSITIVE LOGITS
    çĹĺ
    0.09
    ç¬Ļ
    0.09
    é¢ł
    0.09
    emie
    0.09
    thè
    0.08
    AsStream
    0.08
    ersen
    0.08
    ethylene
    0.08
    reib
    0.08
    å¤ĩ
    0.08
    Activations Density 0.016%

    No Known Activations