© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1019
    Prev
    Next
    INDEX
    Explanations

    License and file extensions

    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
    åįķåħĥ
    -0.24
    Lint
    -0.23
    ple
    -0.23
    venient
    -0.23
     lint
    -0.21
    uen
    -0.21
    .rs
    -0.21
     alma
    -0.21
     Glad
    -0.21
    akt
    -0.21
    POSITIVE LOGITS
    çĥŃ度
    0.25
    ichel
    0.25
     MSD
    0.23
     pong
    0.22
    æ±Ģ
    0.22
    toi
    0.22
    满
    0.22
    езн
    0.22
     Plan
    0.21
    å°Ĭéĩį
    0.21
    Activations Density 0.001%

    No Known Activations