© 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. 19807
    Prev
    Next
    INDEX
    Explanations

    budgetary cuts

    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
    vez
    -0.10
    hart
    -0.09
    ollection
    -0.09
    fare
    -0.09
    outers
    -0.09
    dbg
    -0.09
    åīįæīĢ
    -0.08
    éĩįè¦ģä½ľçĶ¨
    -0.08
    OAD
    -0.08
    legate
    -0.08
    POSITIVE LOGITS
    ary
    0.12
    eer
    0.12
    ting
    0.12
    tle
    0.10
    ters
    0.10
    irectional
    0.10
    ing
    0.10
    ted
    0.10
    imate
    0.09
     ÑģобÑģÑĤвенно
    0.09
    Activations Density 0.011%

    No Known Activations