© 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. 25186
    Prev
    Next
    INDEX
    Explanations

    representation

    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
    å®ļ
    -0.29
    çļĦæľºä¼ļ
    -0.26
    grad
    -0.25
     Brief
    -0.25
    DEF
    -0.25
    ìłľ
    -0.25
    æķĪ
    -0.25
    ease
    -0.25
    -hide
    -0.24
    æĶ¯æŀ¶
    -0.23
    POSITIVE LOGITS
     nowhere
    0.32
    å¼ĢéŨ
    0.30
     mum
    0.28
    å¤ļç§įå½¢å¼ı
    0.26
    .sources
    0.26
    _locked
    0.26
    warts
    0.26
     everywhere
    0.25
    IJèĹı
    0.25
     Frozen
    0.25
    Activations Density 0.001%

    No Known Activations