© 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. 10127
    Prev
    Next
    INDEX
    Explanations

    fossil fuels

    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
    peria
    -0.10
    èĩªæķij
    -0.09
     freed
    -0.08
    idel
    -0.08
    _cre
    -0.08
    å¸Ĥåľºä¸Ĭ
    -0.08
    çijŁ
    -0.08
    -REAL
    -0.08
    èĩ¨
    -0.08
    çĽĺ
    -0.08
    POSITIVE LOGITS
    çŁ³æ²¹
    0.13
    åĮĸçŁ³
    0.12
     fossil
    0.11
    Ñģкоп
    0.11
    rees
    0.10
    åľ°ä¸ĭ
    0.10
     Pale
    0.09
    æŀ¯
    0.09
    åŃIJåŃĻ
    0.09
    çŁ³åĮĸ
    0.09
    Activations Density 0.071%

    No Known Activations