© 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. 19-TRANSCODER-HP
    7. 9285
    Prev
    Next
    INDEX
    Explanations

    age

    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
     EventType
    -0.30
    plier
    -0.29
    Ĭ¶
    -0.29
    .Symbol
    -0.26
    .panel
    -0.26
    ALT
    -0.25
     Logo
    -0.25
    æľįåĬ¡ä¸ļ
    -0.24
    èĹı
    -0.24
    ALTH
    -0.24
    POSITIVE LOGITS
    (rv
    0.27
    овал
    0.25
    ä¸ŃåİŁ
    0.25
     CSL
    0.24
    ifar
    0.24
    (other
    0.23
     flick
    0.23
    ({↵
    0.23
    æĻ
    0.23
    èĢĮ对äºİ
    0.23
    Activations Density 0.073%

    No Known Activations