© 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. 994
    Prev
    Next
    INDEX
    Explanations

    point mutation, substitution, deletion

    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
    åĢį
    -0.10
     Bret
    -0.10
    è¦ģéĹ»
    -0.09
    ä¸Ńå°ı
    -0.09
    aley
    -0.09
    èĥļ
    -0.08
    elter
    -0.08
    _ev
    -0.08
    åħħ
    -0.08
    è§īæĤŁ
    -0.08
    POSITIVE LOGITS
    è·Ŀ
    0.10
    azı
    0.09
    pling
    0.09
    æĹłå£°
    0.09
    IONS
    0.09
    æģIJ
    0.09
    çĸ²
    0.08
    uge
    0.08
    åİŁåŃIJ
    0.08
    åĩ»
    0.08
    Activations Density 0.423%

    No Known Activations