© 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. 25-TRANSCODER-HP
    7. 108962
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isd
    -0.27
    åħīèį£
    -0.26
     Penguin
    -0.26
    äºķ
    -0.26
    isme
    -0.26
    UGHT
    -0.26
     ")[
    -0.25
     Sentence
    -0.23
    ")[
    -0.23
    æĺ¯ä¸Ģ件
    -0.23
    POSITIVE LOGITS
    лÑıеÑĤ
    0.30
    licit
    0.29
    åĺ´è§Ĵ
    0.26
     desteÄŁi
    0.26
    çIJĨæĥ³çļĦ
    0.26
    char
    0.25
    æĤ´
    0.25
    enance
    0.25
    åļ
    0.25
    (enum
    0.24
    Activations Density 0.108%

    No Known Activations

    This feature has no known activations.