© 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. 7215
    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
    .sav
    -0.28
    eti
    -0.26
    itis
    -0.25
    æ´¼
    -0.25
    .ObjectModel
    -0.24
    itaire
    -0.24
    ithub
    -0.23
    åĨ¬å¥¥ä¼ļ
    -0.23
    anian
    -0.23
     egret
    -0.23
    POSITIVE LOGITS
    rah
    0.27
    /fs
    0.27
    èĢģ人家
    0.25
    изаÑĤоÑĢ
    0.25
    èĩ§
    0.25
     tph
    0.24
    bookmark
    0.24
    isas
    0.24
    èĢĮåİ»
    0.24
     psy
    0.23
    Activations Density 0.029%

    No Known Activations