© 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. 107358
    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
     kaz
    -0.30
    ãĤ³ãĥŁ
    -0.26
    åħ¨æĹ¥
    -0.26
    å°ī
    -0.26
     spirit
    -0.25
    emet
    -0.25
     rating
    -0.25
     ratings
    -0.25
     kos
    -0.25
    æĬ±
    -0.25
    POSITIVE LOGITS
    ä»ĸä¼ļ
    0.29
    ens
    0.28
    yor
    0.26
     precursor
    0.26
    blocking
    0.25
    ng
    0.25
     catalyst
    0.24
    à¸Ĭา
    0.24
    æĪijä¼ļ
    0.24
    VR
    0.24
    Activations Density 0.893%

    No Known Activations