© 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. 34539
    Prev
    Next
    INDEX
    Explanations

    sweet descriptions

    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
    çī¹æľĹ
    -0.09
     Whit
    -0.09
     martin
    -0.09
    gende
    -0.09
    AppState
    -0.08
     báºŃt
    -0.08
    èĤĸ
    -0.08
    ãģ£ãģ½
    -0.08
    磶
    -0.08
    tsky
    -0.08
    POSITIVE LOGITS
    çĶľ
    0.17
     sweet
    0.14
    sweet
    0.14
    หวาà¸Ļ
    0.12
     Sweet
    0.12
    çĶľèľľ
    0.12
    çĶľç¾İ
    0.11
    Sweet
    0.11
     ngá»įt
    0.11
     sweetness
    0.10
    Activations Density 0.029%

    No Known Activations