© 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. 40588
    Prev
    Next
    INDEX
    Explanations

    code, documentation

    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
    REA
    -0.26
    roud
    -0.26
    contra
    -0.25
    åįłåľ°éĿ¢ç§¯
    -0.24
     contradiction
    -0.24
     UIViewController
    -0.24
    eus
    -0.24
     wyÅĽ
    -0.24
    brit
    -0.24
    FormData
    -0.24
    POSITIVE LOGITS
    ŀĭ
    0.29
     interrog
    0.28
     aspiration
    0.27
    çĬ¹
    0.26
    atty
    0.26
    uj
    0.25
     yourself
    0.25
    å®ī稳
    0.25
     yourselves
    0.25
    Decor
    0.24
    Activations Density 0.089%

    No Known Activations