© 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. Qwen3-4B
    5. 18-TRANSCODER-HP
    7. 89532
    Prev
    Next
    INDEX
    Explanations

    Text excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .Thread
    -0.26
    iry
    -0.26
     Slut
    -0.25
    ëĭµ
    -0.25
    ndon
    -0.25
    apur
    -0.24
    inery
    -0.24
    ä¸įå¿į
    -0.24
    bery
    -0.23
    rxjs
    -0.23
    POSITIVE LOGITS
     shopper
    0.26
     __________________↵↵
    0.26
    loth
    0.25
    .tcp
    0.24
    æĻ´
    0.24
    -leg
    0.24
    oux
    0.24
    auce
    0.24
    atre
    0.23
    æī§æķĻ
    0.23
    Activations Density 33.662%

    No Known Activations