© 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. 23930
    Prev
    Next
    INDEX
    Explanations

    common short words

    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
    åĨ¬
    -0.31
    å¼Ģæľº
    -0.30
    å¾µ
    -0.30
    å¾ģ
    -0.28
    écoute
    -0.27
    åĩºçĶŁ
    -0.26
    arta
    -0.26
    ibernate
    -0.26
    æŁ¥çľĭæĽ´å¤ļ
    -0.24
    ä¿ĥ
    -0.24
    POSITIVE LOGITS
    fos
    0.27
    imps
    0.27
    BEST
    0.24
     )}↵↵
    0.24
    为ä½ķ
    0.23
    fix
    0.23
    ×
    0.23
    ä¼ļå±ķ
    0.23
    çĴĥ
    0.23
    GRESS
    0.23
    Activations Density 0.002%

    No Known Activations