© 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. 23-TRANSCODER-HP
    7. 24404
    Prev
    Next
    INDEX
    Explanations

    study

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Injected
    -0.27
    çļĦçĶŁåij½
    -0.27
    being
    -0.27
    uns
    -0.27
    ultz
    -0.26
     boon
    -0.25
    switch
    -0.24
    éŸ
    -0.24
    ago
    -0.24
    å¼Ģçİ©ç¬ij
    -0.24
    POSITIVE LOGITS
     quantum
    0.29
    gratis
    0.29
    tlement
    0.28
    esson
    0.27
    .RestController
    0.27
     deeply
    0.27
    ÑĨ
    0.27
     physics
    0.27
     bip
    0.27
    éŀħ
    0.26
    Activations Density 0.039%

    No Known Activations