© 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. 56069
    Prev
    Next
    INDEX
    Explanations

    Ayn Rand, Atlas, Prometheus

    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
    沿
    -0.10
    åĪĿå¿ĥ
    -0.09
     ICT
    -0.09
    磫
    -0.09
     nett
    -0.08
    åĺ±
    -0.08
    esan
    -0.08
    举æŃ¢
    -0.08
    ä»İ严治
    -0.08
    ç»ķ
    -0.08
    POSITIVE LOGITS
    éĴ¢æĿIJ
    0.13
     Steel
    0.11
    éĴ¢éĵģ
    0.10
    Steel
    0.10
    åĮĸ身
    0.09
    éĶ»
    0.09
     steel
    0.09
    便äºİ
    0.09
     peter
    0.09
    åĬĽäºī
    0.09
    Activations Density 0.016%

    No Known Activations