© 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. 35979
    Prev
    Next
    INDEX
    Explanations

    rav/ravelling/ravines

    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
    leine
    -0.09
    resse
    -0.09
    ammen
    -0.09
    LEN
    -0.08
    ctic
    -0.08
    çŀ
    -0.08
    arf
    -0.08
     GPUs
    -0.08
    owe
    -0.08
    swer
    -0.08
    POSITIVE LOGITS
    edException
    0.12
    0.10
    åĽŀé¦ĸ
    0.10
    éĥ¦
    0.10
    缼ä¸ĸ
    0.09
    ably
    0.09
    å£ij
    0.09
     Ñģебе
    0.09
     اÙĦØ£Ùħر
    0.08
    krä
    0.08
    Activations Density 0.004%

    No Known Activations