© 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. 56197
    Prev
    Next
    INDEX
    Explanations

    sudden death or collapse

    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
    enz
    -0.09
    ucha
    -0.09
    uckle
    -0.09
    æĬĺèħ¾
    -0.09
    VIEW
    -0.08
    à¹Ħà¸Ĺย
    -0.08
    hip
    -0.08
    常ãģ«
    -0.08
    ability
    -0.08
    ãģĦãģij
    -0.08
    POSITIVE LOGITS
    aneously
    0.14
    ness
    0.14
    emente
    0.12
    aneous
    0.11
    idad
    0.11
    -death
    0.10
     обÑĢазом
    0.10
    çĹĩ
    0.10
    çªģ
    0.10
    æĢ§çļĦ
    0.10
    Activations Density 0.012%

    No Known Activations