© 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. 24276
    Prev
    Next
    INDEX
    Explanations

    surfaces and coatings

    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
    éľ²å¤©
    -0.27
    emarks
    -0.26
    å¾Ĺä½ı
    -0.26
    çIJĨ解åĴĮ
    -0.26
    æĶ¾æĿ¾
    -0.25
    /Private
    -0.25
     prompts
    -0.25
    cplusplus
    -0.25
     azt
    -0.24
    ç»ıåķĨ
    -0.24
    POSITIVE LOGITS
     with
    0.29
    uge
    0.27
    té
    0.26
    earing
    0.26
    对
    0.25
    çĶ¨äºº
    0.25
    .ip
    0.25
    WithData
    0.25
    ãĥ»
    0.24
    WithURL
    0.24
    Activations Density 0.007%

    No Known Activations