© 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. 27259
    Prev
    Next
    INDEX
    Explanations

    host and cellular interactions

    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
    åĩºèµĦ
    -0.09
    ä¸įè´Ł
    -0.09
    èĥ´
    -0.09
    大家éĥ½åľ¨
    -0.09
    .shtml
    -0.09
    éĿĵ
    -0.09
    æħ°
    -0.09
    æĦŁæ¿Ģ
    -0.09
     Niet
    -0.08
    æĥ³åĪ°
    -0.08
    POSITIVE LOGITS
    宿
    0.16
    hosts
    0.14
     hosts
    0.14
     host
    0.14
    host
    0.13
     Host
    0.12
    Host
    0.12
    _host
    0.12
     HOST
    0.11
    .host
    0.11
    Activations Density 0.374%

    No Known Activations