© 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. 38542
    Prev
    Next
    INDEX
    Explanations

    software installed or loaded

    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
    æĩĭ
    -0.11
    entai
    -0.10
    浪
    -0.10
    çŀij
    -0.09
    atat
    -0.09
    åĬŀæ³ķ
    -0.09
    ä»İåīį
    -0.09
    /pass
    -0.08
    åģ¶å°Ķ
    -0.08
    enta
    -0.08
    POSITIVE LOGITS
     installed
    0.12
    Installed
    0.12
     Installed
    0.12
    å®īè£ħ
    0.12
     onto
    0.10
    installed
    0.10
     downloaded
    0.10
    ANEL
    0.10
    åħĪ导
    0.09
    _installed
    0.09
    Activations Density 0.190%

    No Known Activations