© 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. 23013
    Prev
    Next
    INDEX
    Explanations

    score

    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
    heels
    -0.11
    å¤ĸåĩº
    -0.10
    çĹĺ
    -0.09
    ond
    -0.09
    IAS
    -0.09
    æıŃéľ²
    -0.09
     Theft
    -0.09
    _spinner
    -0.08
    iry
    -0.08
    æij¸
    -0.08
    POSITIVE LOGITS
     score
    0.16
    score
    0.14
    å¾ĹåĪĨ
    0.14
     scores
    0.13
    _score
    0.13
     Score
    0.12
    .score
    0.12
    Score
    0.12
    积åĪĨ
    0.12
    	score
    0.12
    Activations Density 0.046%

    No Known Activations