© 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. 51600
    Prev
    Next
    INDEX
    Explanations

    trade names, secrets, union, affiliations, and events

    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
    otime
    -0.10
    ly
    -0.10
    rud
    -0.09
    Injected
    -0.09
    æ¶Īè´¹éľĢæ±Ĥ
    -0.09
    reur
    -0.09
    iku
    -0.09
    /her
    -0.09
    åºĬä¸Ĭ
    -0.09
    naire
    -0.09
    POSITIVE LOGITS
    -offs
    0.13
    offs
    0.11
    çīºçī²
    0.10
    åĿĬ
    0.10
    bots
    0.10
    ulos
    0.09
    station
    0.09
    able
    0.09
    hawk
    0.09
    backs
    0.09
    Activations Density 0.029%

    No Known Activations