© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6831
    Prev
    Next
    INDEX
    Explanations

    End of event/time period

    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
    lm
    -0.32
     ferr
    -0.26
    Everyone
    -0.24
     Ferr
    -0.24
    å®īåħ¨æĦŁ
    -0.24
    åĩºåİĤ
    -0.24
     Introduced
    -0.23
    lam
    -0.23
    Ñĥй
    -0.23
    æĸ¼
    -0.23
    POSITIVE LOGITS
    TPL
    0.31
    便
    0.27
    ä¸įå¿į
    0.27
    ipro
    0.26
    altung
    0.26
    约è°Ī
    0.25
     HIP
    0.25
    ä¸įæŃ¢
    0.25
     emailing
    0.25
    沧
    0.25
    Activations Density 0.088%

    No Known Activations