© 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. 37738
    Prev
    Next
    INDEX
    Explanations

    Alexandria

    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
    æ´½
    -0.10
    çĻ»å±±
    -0.10
    ILA
    -0.09
    峦
    -0.09
    寸
    -0.09
    izontal
    -0.08
    æĪļ
    -0.08
    常å§Ķ
    -0.08
    éľĩèį¡
    -0.08
    SCII
    -0.08
    POSITIVE LOGITS
    å·´å·´
    0.10
    naire
    0.09
    aires
    0.09
    -based
    0.09
    uries
    0.09
    arious
    0.08
    onor
    0.08
    ogle
    0.08
    odem
    0.08
    reen
    0.08
    Activations Density 0.004%

    No Known Activations