© 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. 32-TRANSCODER-HP
    7. 43724
    Prev
    Next
    INDEX
    Explanations

    Dates or numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åħ¥
    -0.28
    åĴĮæĬĢæľ¯
    -0.27
    istar
    -0.26
    ä¸Ģä¸ĸ
    -0.25
    Business
    -0.25
     urge
    -0.25
    istency
    -0.25
    _business
    -0.24
    æ¾İæ¹ĥæĸ°éĹ»
    -0.24
     Bond
    -0.24
    POSITIVE LOGITS
    ç¦ıçĶ°
    0.27
    碱
    0.26
    Initializer
    0.26
    AILY
    0.26
    Alg
    0.25
    aily
    0.24
    alg
    0.24
    御
    0.23
     Prix
    0.23
    æ·ĭ
    0.23
    Activations Density 0.001%

    No Known Activations