© 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. 41952
    Prev
    Next
    INDEX
    Explanations

    International topics and places

    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
    æ¡£
    -0.27
    illi
    -0.27
     dime
    -0.27
     ëĭµë³Ģ
    -0.26
    umi
    -0.26
    ä¸ĢæĬ¹
    -0.26
    è°¦
    -0.26
    umed
    -0.26
    clr
    -0.25
    礼仪
    -0.25
    POSITIVE LOGITS
    ture
    0.28
     inv
    0.27
    ine
    0.26
    é¾Ļ
    0.26
    çī©
    0.25
    驾车
    0.25
    GST
    0.25
    INO
    0.25
     '../../../../../
    0.24
    пеÑĩаÑĤ
    0.24
    Activations Density 0.001%

    No Known Activations