© 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. 30038
    Prev
    Next
    INDEX
    Explanations

    Apple

    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
    dad
    -0.31
    ÑĤок
    -0.29
     negot
    -0.28
    æĹłåħ³
    -0.26
    è¿IJ
    -0.26
    为æ°ij
    -0.26
    zens
    -0.25
    illion
    -0.25
    åŁºç¡Ģä¸Ĭ
    -0.25
     subdiv
    -0.24
    POSITIVE LOGITS
    æĿĢæīĭ
    0.25
    æĺ¯æĢİæł·
    0.25
     chests
    0.25
    代è¨Ģ人
    0.25
     victories
    0.24
    ientes
    0.24
     Primer
    0.24
     rant
    0.23
    antine
    0.23
     haystack
    0.23
    Activations Density 1.344%

    No Known Activations