© 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. 48997
    Prev
    Next
    INDEX
    Explanations

    sense of

    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
    ter
    -0.08
    ARAM
    -0.08
    icity
    -0.08
    ied
    -0.08
    iled
    -0.08
    tr
    -0.08
    ilon
    -0.08
    tra
    -0.08
    shi
    -0.08
    款
    -0.08
    POSITIVE LOGITS
    lessly
    0.13
    uale
    0.11
    ãģ¾ãģĦ
    0.11
    less
    0.10
    èĩ¾
    0.10
    ouble
    0.10
     пÑĢид
    0.10
    acre
    0.10
    amedi
    0.10
    esta
    0.10
    Activations Density 0.007%

    No Known Activations