© 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. 30-TRANSCODER-HP
    7. 96750
    Prev
    Next
    INDEX
    Explanations

    code snippets and XML

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    表çİ°
    -0.29
     wh
    -0.27
     etc
    -0.26
     immediate
    -0.26
    çŃīçŃī
    -0.26
    许
    -0.25
     analog
    -0.25
     feedback
    -0.25
    -0.25
     amongst
    -0.25
    POSITIVE LOGITS
    idar
    0.25
    å±Ģå±Ģéķ¿
    0.24
    wise
    0.24
    æĺİå¹´
    0.24
    commission
    0.24
    ayar
    0.23
    å®ĵ
    0.23
    nelle
    0.23
    acier
    0.23
    icode
    0.23
    Activations Density 1.027%

    No Known Activations