© 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. 14-TRANSCODER-HP
    7. 40815
    Prev
    Next
    INDEX
    Explanations

    Columbus

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    为åħ¶
    -0.25
     full
    -0.25
    å±ħ
    -0.25
    æĭ¼
    -0.25
    apr
    -0.25
    åIJİçļĦ
    -0.24
    ofile
    -0.23
    饽
    -0.23
    éĥ¨
    -0.23
    olini
    -0.23
    POSITIVE LOGITS
    illo
    0.28
    илÑĮно
    0.27
    é¡·
    0.25
    èľĥ
    0.24
    寰
    0.24
    (aa
    0.23
    è£ĺ
    0.23
    æ²Ĩ
    0.23
    ier
    0.23
    IGGER
    0.23
    Activations Density 0.230%

    No Known Activations