© 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. 40952
    Prev
    Next
    INDEX
    Explanations

    university

    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
    eners
    -0.27
     Platz
    -0.27
    æĶ¾åĪ°
    -0.26
    ItemSelected
    -0.26
    ,’”
    -0.25
    æĮĩå¼ķ
    -0.24
    è¾¹ç¼ĺ
    -0.24
    ä½ij
    -0.24
    é¢Ĩ导
    -0.23
    æ±
    -0.23
    POSITIVE LOGITS
    åľ¨è¿ĩ渡
    0.27
    onia
    0.26
    ta
    0.25
    еÑĢÑĮ
    0.25
    èļ§
    0.25
     AppState
    0.24
    ä»İæł¹æľ¬
    0.24
     nextState
    0.24
     nightly
    0.23
    tape
    0.23
    Activations Density 1.777%

    No Known Activations