© 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. 95972
    Prev
    Next
    INDEX
    Explanations

    invention and development

    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
    è¡¥åħħ
    -0.29
     Exist
    -0.26
     assisted
    -0.26
     exist
    -0.26
    å®īæİĴ
    -0.25
     indirect
    -0.25
    exist
    -0.24
    Exist
    -0.24
    -pic
    -0.24
    tr
    -0.24
    POSITIVE LOGITS
     devised
    0.48
     developed
    0.44
     invented
    0.40
     Developed
    0.38
     devise
    0.38
    -develop
    0.36
     devel
    0.36
    develop
    0.34
     identified
    0.33
    å¼Ģåıij
    0.32
    Activations Density 0.149%

    No Known Activations