© 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. 18-TRANSCODER-HP
    7. 89473
    Prev
    Next
    INDEX
    Explanations

    Attempts, failures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     именно
    -0.27
    ä¸įåĩĨ
    -0.26
    äºīåıĸ
    -0.25
     dips
    -0.25
    åĴĮåħ¶ä»ĸ
    -0.24
     melhor
    -0.24
    upal
    -0.23
    ubo
    -0.23
    uly
    -0.23
     foot
    -0.23
    POSITIVE LOGITS
    åį¿
    0.25
    è¾¹ä¸Ĭ
    0.25
    oge
    0.25
    ä½ĵçİ°åĩº
    0.25
    è¾¹
    0.24
    oven
    0.24
     Latina
    0.23
     bun
    0.23
    åĢ¼å¾Ĺä¸ĢæıIJ
    0.23
     sigu
    0.23
    Activations Density 2.372%

    No Known Activations