© 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. 88688
    Prev
    Next
    INDEX
    Explanations

    quotes

    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
     tend
    -0.28
     fucking
    -0.28
    éĻ¤éĿŀ
    -0.27
     waivers
    -0.26
    bow
    -0.26
    owler
    -0.25
    =>'
    -0.25
    bows
    -0.24
    tails
    -0.24
    ipient
    -0.24
    POSITIVE LOGITS
    actors
    0.28
    eda
    0.26
    -dat
    0.26
     stad
    0.26
     vX
    0.24
    顶
    0.24
    ĵį
    0.24
    ид
    0.24
     Borg
    0.24
     вÑĢем
    0.23
    Activations Density 23.072%

    No Known Activations