© 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. 89413
    Prev
    Next
    INDEX
    Explanations

    select

    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
    assa
    -0.29
    lah
    -0.28
    åħ¨ä½ĵ
    -0.25
     bulld
    -0.24
    íĭ´
    -0.24
    æѤç§į
    -0.24
    /null
    -0.24
    uil
    -0.24
    éĻ
    -0.23
     sociology
    -0.23
    POSITIVE LOGITS
    ç»ĵå°¾
    0.25
     movement
    0.24
     nom
    0.23
     perceived
    0.23
    umont
    0.23
    æĪĺèĥľ
    0.23
    çĻ½é©¬
    0.23
     bounced
    0.23
    nom
    0.23
    çªģåĽ´
    0.23
    Activations Density 10.565%

    No Known Activations