© 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. 29955
    Prev
    Next
    INDEX
    Explanations

    URLs and filenames

    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
    anoia
    -0.28
     rugs
    -0.25
    nah
    -0.25
    omat
    -0.25
    thesize
    -0.24
    vasive
    -0.24
    åĬŀåħ¬å®¤
    -0.24
     movies
    -0.24
     Secret
    -0.23
    èŀ¨
    -0.23
    POSITIVE LOGITS
     tun
    0.28
     convertible
    0.27
    å¹²
    0.25
    ç±į
    0.25
    icket
    0.24
     ÐĽÐµ
    0.24
    äºij计ç®Ĺ
    0.24
     cá»ij
    0.24
    –↵↵
    0.23
    leitung
    0.23
    Activations Density 0.134%

    No Known Activations