© 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. 41678
    Prev
    Next
    INDEX
    Explanations

    The

    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
    ums
    -0.27
     bulk
    -0.25
    äºİæĺ¯æĪij
    -0.24
    åīįä¸Ģ天
    -0.24
    ç§ij
    -0.24
    own
    -0.24
    iqu
    -0.24
    Ñģла
    -0.24
    驼
    -0.24
    owns
    -0.23
    POSITIVE LOGITS
    USR
    0.26
     bè
    0.25
    otty
    0.25
    LOUR
    0.25
    åıĺæĢģ
    0.24
    èĦļ
    0.24
    obi
    0.23
    atori
    0.23
     dh
    0.23
    æ°ª
    0.23
    Activations Density 0.010%

    No Known Activations