© 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. 23285
    Prev
    Next
    INDEX
    Explanations

    festival, limited editions, Pacific time, parental guidance

    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
    arshal
    -0.10
     ÐĶе
    -0.09
    oppable
    -0.09
     stadiums
    -0.08
    istine
    -0.08
    代è¨Ģ
    -0.08
    _DRV
    -0.08
    골
    -0.08
    ifestyle
    -0.08
    aryl
    -0.08
    POSITIVE LOGITS
     queer
    0.09
     guerr
    0.09
    OfMonth
    0.08
    ç¿ĺ
    0.08
    å¢Ļ
    0.08
    acao
    0.08
    punk
    0.07
    èīºæľ¯å®¶
    0.07
     neighborhood
    0.07
    游åĩ»
    0.07
    Activations Density 0.225%

    No Known Activations