© 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. 7088
    Prev
    Next
    INDEX
    Explanations

    -ish suffix

    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
    леÑĤ
    -0.10
    age
    -0.09
    angelo
    -0.09
    ange
    -0.09
    ä»·åĢ¼
    -0.08
     hele
    -0.08
    гад
    -0.08
    ivist
    -0.08
    WND
    -0.08
    éªĭ
    -0.08
    POSITIVE LOGITS
    ness
    0.15
    NESS
    0.11
    -looking
    0.10
    åĬŁè¯¾
    0.09
    ity
    0.09
     gì
    0.09
    wares
    0.08
    ·»
    0.08
     Pur
    0.08
    yll
    0.08
    Activations Density 0.010%

    No Known Activations