© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7638
    Prev
    Next
    INDEX
    Explanations

    Punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lig
    -0.30
    anner
    -0.27
    enc
    -0.26
    shortcode
    -0.26
    archs
    -0.26
    éĥ½è§īå¾Ĺ
    -0.25
    wer
    -0.25
    mare
    -0.24
    arch
    -0.23
    产åĵģ
    -0.23
    POSITIVE LOGITS
    hamster
    0.28
     amo
    0.27
    REM
    0.26
    inflate
    0.26
    èķ¾
    0.26
    çIJĨç§ij
    0.26
    +xml
    0.25
    åij¦
    0.25
    Rem
    0.25
     am
    0.25
    Activations Density 0.032%

    No Known Activations