© 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. 40512
    Prev
    Next
    INDEX
    Explanations

    structure

    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
    åªĴ
    -0.28
     oldest
    -0.26
    Makes
    -0.26
    MBER
    -0.26
    usive
    -0.25
     permanently
    -0.24
     SC
    -0.24
    akt
    -0.24
     immersed
    -0.24
    boss
    -0.23
    POSITIVE LOGITS
    еÑģÑģ
    0.28
    nic
    0.27
    letic
    0.27
     Retreat
    0.26
    suite
    0.26
     Federation
    0.26
    ERAL
    0.26
     nic
    0.25
    ä¹±
    0.25
     lã
    0.25
    Activations Density 1.071%

    No Known Activations