© 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. 8708
    Prev
    Next
    INDEX
    Explanations

    Code and miscellaneous text

    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
    èĭŀ
    -0.34
    ’S
    -0.28
     niezb
    -0.27
    XP
    -0.25
     oxygen
    -0.24
    å¹²æ¶ī
    -0.23
     Oxygen
    -0.23
    æĬķ注
    -0.23
    å¹¿åľº
    -0.23
    æ°§
    -0.23
    POSITIVE LOGITS
    æĭĩ
    0.27
    haft
    0.26
    @g
    0.25
     tim
    0.25
    <=$
    0.24
    ogy
    0.24
    emu
    0.24
     Loader
    0.24
    Rnd
    0.24
     personals
    0.23
    Activations Density 4.494%

    No Known Activations