© 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. 19613
    Prev
    Next
    INDEX
    Explanations

    adaptation and adjustment

    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
    è¾Ł
    -0.09
     ÑĢÑĥк
    -0.09
    å¼Ģè¾Ł
    -0.09
    -sizing
    -0.08
    uron
    -0.08
    Hands
    -0.08
     Duty
    -0.08
    activated
    -0.08
    astle
    -0.08
    åį±å®³
    -0.08
    POSITIVE LOGITS
    éĢĤåºĶ
    0.26
     adaptation
    0.15
    adapt
    0.15
     adapt
    0.14
     Adapt
    0.13
    èŀįåħ¥
    0.12
     adapting
    0.12
     adap
    0.11
     assim
    0.11
     adapted
    0.11
    Activations Density 0.083%

    No Known Activations