© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 315
    Prev
    Next
    INDEX
    Explanations

    segments and lengths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    .hm
    -0.24
    borg
    -0.24
    ç«ĭä½ĵ
    -0.24
    ief
    -0.23
    亲
    -0.23
    Dig
    -0.23
    semb
    -0.23
     Tyson
    -0.22
    nore
    -0.22
    zes
    -0.22
    POSITIVE LOGITS
    åħ¨éķ¿
    0.61
    éķ¿åº¦
    0.55
     length
    0.53
    段
    0.52
     segment
    0.51
    length
    0.50
     segments
    0.48
    两端
    0.47
    è¿Ļ段
    0.46
     lengths
    0.45
    Activations Density 0.398%

    No Known Activations