© 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. 62500
    Prev
    Next
    INDEX
    Explanations

    thank you

    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
    igel
    -0.10
    _UNS
    -0.09
    tle
    -0.08
    andre
    -0.08
    egot
    -0.08
    åĨ¼
    -0.08
    åħ³éĶ®æŶåĪ»
    -0.08
    ail
    -0.08
    gradable
    -0.08
    ügen
    -0.08
    POSITIVE LOGITS
    ixed
    0.10
    sgiving
    0.10
    isha
    0.09
    .ResponseBody
    0.09
    ably
    0.09
    ssc
    0.09
    asaki
    0.09
    å¤Ł
    0.09
    à¸Ńะ
    0.09
    ousands
    0.08
    Activations Density 0.032%

    No Known Activations