© 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. 20-TRANSCODER-HP
    7. 130712
    Prev
    Next
    INDEX
    Explanations

    General writing / discussion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĦıè§ģåıįé¦Ī
    -0.29
     spontaneous
    -0.27
    ç½ijç»ľä¼łæĴŃ
    -0.26
    #End
    -0.26
    anean
    -0.26
    æķĪåºĶ
    -0.26
     testcase
    -0.25
    hoc
    -0.25
    /Page
    -0.24
     realise
    -0.24
    POSITIVE LOGITS
    æĮĩ
    0.33
    æĮĩçĶ²
    0.28
    RLF
    0.27
    surface
    0.27
    clin
    0.26
    åĭ¾
    0.25
    dbl
    0.25
    å¾®éĩıåħĥç´ł
    0.24
    åĵģæł¼
    0.24
    inja
    0.24
    Activations Density 11.114%

    No Known Activations