© 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. 10877
    Prev
    Next
    INDEX
    Explanations

    radio station identifiers

    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
     TV
    -0.12
    çĶµè§Ĩ
    -0.12
    _tv
    -0.11
    ãĥĨãĥ¬ãĥĵ
    -0.11
     Television
    -0.11
    çľĭçĶµè§Ĩ
    -0.11
    çī¢
    -0.10
     television
    -0.10
     televis
    -0.10
    TV
    -0.10
    POSITIVE LOGITS
    è¯ł
    0.10
    raq
    0.09
    æŀ¶åŃIJ
    0.09
    ç¾½
    0.09
    .Require
    0.09
    ä¸Ĭåīį
    0.09
    ADVERTISEMENT
    0.09
    åĺĺ
    0.08
    .backends
    0.08
    _RSP
    0.08
    Activations Density 0.092%

    No Known Activations