© 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. 22-TRANSCODER-HP
    7. 129403
    Prev
    Next
    INDEX
    Explanations

    apply

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å®ļçĤ¹
    -0.29
    cente
    -0.27
    icha
    -0.26
    orig
    -0.26
    izio
    -0.25
    _lazy
    -0.25
    rst
    -0.24
    åIJ±
    -0.24
    åĽ½éģĵ
    -0.24
    ndef
    -0.24
    POSITIVE LOGITS
    stract
    0.31
    iba
    0.25
    ç¬ĶèĢħ
    0.25
    ä»Ģä¹Īæł·çļĦ
    0.24
    flash
    0.24
    ä¸Ģå®ļçļĦ
    0.24
    äºĨä¸ĢäºĽ
    0.24
    .ib
    0.23
    çĶµæ±ł
    0.23
     certain
    0.23
    Activations Density 0.029%

    No Known Activations