© 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. 41186
    Prev
    Next
    INDEX
    Explanations

    Data or code passages

    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
    rip
    -0.27
    andal
    -0.27
    jeta
    -0.27
    aine
    -0.27
     firm
    -0.25
     rainbow
    -0.25
    ajan
    -0.25
    ä¸įæľį
    -0.25
    å°¾
    -0.25
    agh
    -0.25
    POSITIVE LOGITS
    ä¸įçĶ¨
    0.27
    éĻ¢éķ¿
    0.26
    该éĻ¢
    0.25
    æĹ¢åı¯ä»¥
    0.25
    带头人
    0.25
    .setProgress
    0.25
    éĩijå¸ģ
    0.24
    使
    0.24
    常年
    0.24
    马åĪº
    0.24
    Activations Density 0.087%

    No Known Activations