© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51593
    Prev
    Next
    INDEX
    Explanations

    Coach followed by a name

    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
    ities
    -0.09
    istic
    -0.09
    ized
    -0.09
     Ñģобой
    -0.09
    iance
    -0.09
    ìłģìľ¼ë¡ľ
    -0.09
    alk
    -0.08
    èµħ
    -0.08
    ties
    -0.08
    çºł
    -0.08
    POSITIVE LOGITS
    lems
    0.12
    åĵ¡
    0.11
    ëĭĺ
    0.10
    suite
    0.10
    راس
    0.09
    pls
    0.09
    mium
    0.09
    mans
    0.09
    妣
    0.09
    ðŁı»
    0.09
    Activations Density 0.010%

    No Known Activations