© 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. 41232
    Prev
    Next
    INDEX
    Explanations

    Professional/academic contexts

    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
     incarcer
    -0.28
     lex
    -0.27
    alley
    -0.26
    åŁºåĩĨ
    -0.26
    ocrin
    -0.26
    enheim
    -0.25
    cac
    -0.24
    afe
    -0.24
     Cabin
    -0.24
    ramework
    -0.24
    POSITIVE LOGITS
    cest
    0.28
    åĬĽè¿ĺæĺ¯
    0.28
     states
    0.27
    Ĥ¤
    0.27
    åĬĽ
    0.27
    kol
    0.27
    ball
    0.26
    html
    0.26
    bul
    0.25
     Unexpected
    0.25
    Activations Density 1.776%

    No Known Activations