© 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. 31070
    Prev
    Next
    INDEX
    Explanations

    item following specific tokens

    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
    born
    -0.10
    rid
    -0.09
    èIJĭ
    -0.09
    BOR
    -0.09
    _INET
    -0.08
    ãĥ¢ãĥİ
    -0.08
    utters
    -0.08
    åijĬ
    -0.08
    é©»
    -0.08
    olon
    -0.08
    POSITIVE LOGITS
    ä¸Ģ个éĹ®é¢ĺ
    0.10
    ENTITY
    0.09
    aroo
    0.09
    åĻªå£°
    0.08
    饼干
    0.08
    cake
    0.08
    endez
    0.08
    วล
    0.08
    é»»
    0.08
    大äºĭ
    0.08
    Activations Density 0.055%

    No Known Activations