© 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. 6111
    Prev
    Next
    INDEX
    Explanations

    Code and data

    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
    orelease
    -0.28
     cou
    -0.26
    ool
    -0.26
    jÄħ
    -0.26
    æ·¹
    -0.25
     ska
    -0.24
    æį¢åıĸ
    -0.24
    è¾ĩ
    -0.24
    af
    -0.24
    uely
    -0.23
    POSITIVE LOGITS
    æ®ĸ
    0.28
     yours
    0.26
    ãģ©ãģĨ
    0.26
     Mercer
    0.26
    çݯç»ķ
    0.25
     Yours
    0.25
    æŀ¶åŃIJ
    0.25
    ä¸įæĢķ
    0.24
    缪
    0.24
    cratch
    0.24
    Activations Density 0.022%

    No Known Activations