© 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. 7590
    Prev
    Next
    INDEX
    Explanations

    ran into problem/issue/trouble

    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
    æݧ
    -0.09
    adoras
    -0.09
    aan
    -0.08
    åĺĪ
    -0.08
    çķĮ第ä¸Ģ
    -0.08
    را
    -0.08
    ä¸
    -0.08
    ENCY
    -0.08
     Invitation
    -0.08
    omaly
    -0.08
    POSITIVE LOGITS
    ogo
    0.11
    ä¸Ģéĺµ
    0.10
    pping
    0.09
     issues
    0.08
    æ·Ļ
    0.08
     situations
    0.08
    neau
    0.08
     trouble
    0.08
    old
    0.08
     Cock
    0.08
    Activations Density 0.008%

    No Known Activations