© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6558
    Prev
    Next
    INDEX
    Explanations

    code or technical descriptions

    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
    æ°¾
    -0.30
     assignable
    -0.25
    ä¸ĢéĹª
    -0.25
    ulado
    -0.25
    åĻĹ
    -0.25
    ÑıÑĤи
    -0.24
     Swansea
    -0.24
    æ±¾
    -0.24
    ñ
    -0.24
    aina
    -0.24
    POSITIVE LOGITS
     worth
    0.27
    è¡Ĺ
    0.27
     gig
    0.25
    ir
    0.25
    ent
    0.25
     [("
    0.24
     ↵
    0.24
     street
    0.24
    å¸ĥ
    0.24
     <
    0.24
    Activations Density 0.023%

    No Known Activations