© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51993
    Prev
    Next
    INDEX
    Explanations

    political parties

    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
    å¾·èĤ²
    -0.10
    (priv
    -0.10
    åį»
    -0.09
    è°ı
    -0.09
     priv
    -0.09
     Priv
    -0.09
    burger
    -0.09
    èı½
    -0.09
    pron
    -0.09
    è£ķ
    -0.09
    POSITIVE LOGITS
     party
    0.12
     parties
    0.12
     Party
    0.11
     Parties
    0.11
    _party
    0.11
    Party
    0.10
    æ´¾
    0.10
    .party
    0.10
    party
    0.10
    åĽ¢ä½ĵ
    0.10
    Activations Density 0.188%

    No Known Activations