© 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. 88911
    Prev
    Next
    INDEX
    Explanations

    Digits

    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
     santa
    -0.25
    è´¨éĩıéĹ®é¢ĺ
    -0.24
    fbe
    -0.24
    fs
    -0.24
    å¹
    -0.24
    onte
    -0.24
    :o
    -0.24
    **)
    -0.23
    uman
    -0.23
    èī®
    -0.23
    POSITIVE LOGITS
    vern
    0.27
    OPS
    0.26
    kers
    0.25
    çĽĴåŃIJ
    0.24
     vern
    0.24
    æĶ¶æķĽ
    0.24
    kul
    0.24
    ç´¯äºĨ
    0.24
    hort
    0.24
    antro
    0.24
    Activations Density 2.674%

    No Known Activations