© 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. 8728
    Prev
    Next
    INDEX
    Explanations

    Pronouns

    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
    elize
    -0.30
    LOPT
    -0.28
    eos
    -0.28
    eer
    -0.27
    ëĭ¤ê°Ģ
    -0.27
    å°ijåIJĥ
    -0.26
    CK
    -0.26
    缩çŁŃ
    -0.25
    EFR
    -0.24
    ê¼´
    -0.24
    POSITIVE LOGITS
    çĥ§
    0.27
    _quad
    0.26
    Quad
    0.25
     vot
    0.25
     braking
    0.24
    æ¼Ĥ
    0.24
    çĦ¶æĺ¯
    0.23
    æĴĤ
    0.23
     manual
    0.23
    logging
    0.23
    Activations Density 0.058%

    No Known Activations