© 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. 22851
    Prev
    Next
    INDEX
    Explanations

    Two

    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
    éĤ¦
    -0.27
    alk
    -0.27
    å²ģ以ä¸ĭ
    -0.26
    chor
    -0.26
    èĢķèĢĺ
    -0.26
    åŁļ
    -0.26
    èĿł
    -0.25
    å¹´ä¹ĭä¹ħ
    -0.24
     bis
    -0.24
    ocop
    -0.24
    POSITIVE LOGITS
    fts
    0.27
    (clock
    0.26
    åĽĽäºĶ
    0.25
    ãģĭãģijãģ¦
    0.25
    ights
    0.25
    تا
    0.25
    å±Ģ
    0.24
    大
    0.24
    iatric
    0.24
     four
    0.24
    Activations Density 0.004%

    No Known Activations