© 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. 88854
    Prev
    Next
    INDEX
    Explanations

    code

    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
    utive
    -0.30
    afi
    -0.26
     correspond
    -0.25
    æĸĩåĮĸåĴĮ
    -0.25
    gap
    -0.24
    çݯæ¯Ķ
    -0.24
    ulsive
    -0.23
    =cut
    -0.23
    oph
    -0.23
     Patrol
    -0.23
    POSITIVE LOGITS
    laden
    0.29
    utschen
    0.28
    rot
    0.27
    ERING
    0.26
    errupted
    0.25
    计ç®ĹåĻ¨
    0.25
    ucker
    0.25
    å¨ī
    0.25
    ngth
    0.25
    åĿļ
    0.24
    Activations Density 42.888%

    No Known Activations