© 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. 12-TRANSCODER-HP
    7. 23682
    Prev
    Next
    INDEX
    Explanations

    sensitive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ingt
    -0.27
    åħ¼
    -0.27
    绦
    -0.26
    ubar
    -0.26
    skin
    -0.24
    imd
    -0.24
    isky
    -0.24
     ['$
    -0.24
    alt
    -0.24
    altung
    -0.24
    POSITIVE LOGITS
    æĤ¬å´ĸ
    0.28
    å¾Ĵ
    0.26
    å¤§èµĽ
    0.26
    paralle
    0.25
    stype
    0.25
    èĢĥ
    0.25
    ä¸įéĢļ
    0.24
     goof
    0.24
     electr
    0.23
    ARAM
    0.23
    Activations Density 0.016%

    No Known Activations