© 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. 29708
    Prev
    Next
    INDEX
    Explanations

    need

    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
    IRR
    -0.27
    FromBody
    -0.26
    boot
    -0.26
    Unmount
    -0.26
    _fw
    -0.25
    placement
    -0.25
    ноÑģÑĤ
    -0.25
    edb
    -0.25
     ($)
    -0.25
     HeaderComponent
    -0.25
    POSITIVE LOGITS
    éĿ¢åĮħ
    0.29
    ÑĮÑıн
    0.29
     originally
    0.29
    æłĹ
    0.28
    æĥĭ
    0.27
    pire
    0.27
    è¥Ħ
    0.26
     hurt
    0.26
    æĥĬåĸľ
    0.26
    &M
    0.25
    Activations Density 2.459%

    No Known Activations