© 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. 40331
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    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
     prof
    -0.29
    TypeId
    -0.27
    è¾¾
    -0.27
    åĽłåľ°
    -0.27
    PD
    -0.24
     дол
    -0.24
     dimension
    -0.24
    MIT
    -0.24
    Prof
    -0.24
    Notes
    -0.24
    POSITIVE LOGITS
    chor
    0.30
    gnore
    0.25
    ".↵↵↵↵
    0.24
    }\.[
    0.24
     spectator
    0.23
    ervo
    0.23
    å¹²éĥ¨
    0.23
    isoft
    0.23
     PREF
    0.23
    locales
    0.23
    Activations Density 0.428%

    No Known Activations