© 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. 19901
    Prev
    Next
    INDEX
    Explanations

    Apollo and related medical/scientific terms

    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
    ãĥ£
    -0.10
    ï¸ı
    -0.10
    ÑĢÑıд
    -0.10
    lessly
    -0.10
    åīįçŀ»
    -0.09
    å¨ĥå¨ĥ
    -0.09
    ampo
    -0.09
    è¿ŀäºij
    -0.09
    ual
    -0.09
    çļ¿
    -0.09
    POSITIVE LOGITS
    hower
    0.10
    strained
    0.10
    umn
    0.10
    sing
    0.09
    anism
    0.09
    Ñīе
    0.09
    ìį¨
    0.09
    odus
    0.09
     minded
    0.08
    legt
    0.08
    Activations Density 0.006%

    No Known Activations