© 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. 24424
    Prev
    Next
    INDEX
    Explanations

    Copyright/licensing documentation

    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
     Gilles
    -0.28
    estate
    -0.25
    pios
    -0.25
    æĽ³
    -0.25
    ikers
    -0.24
    Ñĥй
    -0.24
    parsers
    -0.24
    icians
    -0.24
    [arr
    -0.23
    drag
    -0.23
    POSITIVE LOGITS
    è¯ģ书
    0.37
     certificates
    0.36
    åIJįçīĩ
    0.34
    åį¡çīĩ
    0.34
     certificate
    0.32
     invoices
    0.32
    åĩºçİ°åľ¨
    0.32
    åıij票
    0.30
    Certificates
    0.30
     associative
    0.29
    Activations Density 0.018%

    No Known Activations