© 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. 51212
    Prev
    Next
    INDEX
    Explanations

    fraction / fractional

    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
    irus
    -0.11
    åĬ¾
    -0.10
    yer
    -0.10
    thic
    -0.09
    èµİ
    -0.09
    ì¤Ħ
    -0.08
    acic
    -0.08
    ãĤĴæİ¢
    -0.08
    osterone
    -0.08
    å³Ĵ
    -0.08
    POSITIVE LOGITS
    .gms
    0.11
    累累
    0.11
    ation
    0.10
    edList
    0.10
    ToFit
    0.10
    _beam
    0.10
    OfSize
    0.10
     Ñģобой
    0.09
    atos
    0.09
    nel
    0.09
    Activations Density 0.042%

    No Known Activations