© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7201
    Prev
    Next
    INDEX
    Explanations

    radio station callsigns with FM or AM

    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
    stile
    -0.10
    é«®
    -0.09
    æīįæľī
    -0.09
    å¿«
    -0.08
    è¹Ħ
    -0.08
    oji
    -0.08
    Toolkit
    -0.08
    çī¯
    -0.08
    åįĩ温
    -0.08
     Midlands
    -0.08
    POSITIVE LOGITS
    çĭ®åŃIJ
    0.08
    å®ı
    0.08
    reater
    0.08
    çłĶåıijä¸Ńå¿ĥ
    0.08
    ä¸įæĩĪ
    0.08
    gee
    0.08
    iane
    0.08
    ãģĬãģĭãģĴ
    0.08
    ä¸ĩäºĭ
    0.07
    ropolitan
    0.07
    Activations Density 0.046%

    No Known Activations