© 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. 39852
    Prev
    Next
    INDEX
    Explanations

    incidence

    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
    ereum
    -0.29
     Bowen
    -0.27
     hoops
    -0.27
     Thur
    -0.26
    xic
    -0.25
    éķĩæĶ¿åºľ
    -0.25
    IMA
    -0.24
    ëĵ¬
    -0.24
     LETTER
    -0.24
    å³»
    -0.24
    POSITIVE LOGITS
    addy
    0.28
     rub
    0.27
    ANTE
    0.27
     Salt
    0.27
     adv
    0.26
    adv
    0.26
    -focused
    0.26
    è¾ĵ
    0.24
     salt
    0.23
    .pa
    0.23
    Activations Density 3.465%

    No Known Activations