© 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. 9165
    Prev
    Next
    INDEX
    Explanations

    Web page content snippets

    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
    variants
    -0.27
     equ
    -0.26
    ÑĩнаÑı
    -0.25
     Câm
    -0.25
    çļĦä¸ĢåĪĩ
    -0.25
    adel
    -0.25
    Levels
    -0.25
     (!_
    -0.24
    å¾Ĺä½ı
    -0.24
    lose
    -0.24
    POSITIVE LOGITS
    min
    0.26
     OnInit
    0.26
    mins
    0.25
    лан
    0.25
    -xs
    0.24
    pered
    0.24
     borrowed
    0.24
    _TXT
    0.24
    mina
    0.24
    วà¸Ķ
    0.24
    Activations Density 0.001%

    No Known Activations