© 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. 50898
    Prev
    Next
    INDEX
    Explanations

    clearance or clarity descriptor

    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
    å³Ń
    -0.09
    æĶ¯
    -0.09
    кÑĢаÑĤ
    -0.09
    çĪ»
    -0.08
    ãĥĦ
    -0.08
    __((
    -0.08
     Klaus
    -0.08
     mature
    -0.08
    ectomy
    -0.08
    æĺİç¡®äºĨ
    -0.08
    POSITIVE LOGITS
    opens
    0.12
    ances
    0.10
    对åŃ©åŃIJ
    0.10
    å¤į
    0.10
    ings
    0.10
    neck
    0.09
    çĴ©
    0.09
     clear
    0.09
    neas
    0.09
    é¢Ĩè·ij
    0.09
    Activations Density 0.025%

    No Known Activations