© 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. 9-TRANSCODER-HP
    7. 29867
    Prev
    Next
    INDEX
    Explanations

    countries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĬĤ
    -0.29
     imageName
    -0.27
    æĺķ
    -0.27
    æ²»çĸĹæĸ¹æ³ķ
    -0.26
    unos
    -0.24
    лÑĥÑĪ
    -0.24
     rich
    -0.24
    LOPT
    -0.24
    atie
    -0.23
    -grow
    -0.23
    POSITIVE LOGITS
     enjo
    0.27
    ç·¨
    0.25
    inc
    0.25
    éĢļè¡Į
    0.25
    \base
    0.25
     пÑĥ
    0.24
    LR
    0.24
    ç¼ĸ
    0.24
     Contributors
    0.24
    æī¹ç¤º
    0.24
    Activations Density 1.198%

    No Known Activations