© 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. 87857
    Prev
    Next
    INDEX
    Explanations

    slow change

    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
    idian
    -0.29
    åıijèµ·
    -0.25
    suming
    -0.25
    è«®
    -0.25
    iliate
    -0.24
    åģĥ
    -0.24
    ensive
    -0.24
    etch
    -0.24
    WAY
    -0.24
    etwork
    -0.24
    POSITIVE LOGITS
    spoken
    0.25
     diminishing
    0.24
     closing
    0.24
     pattern
    0.23
     Gaga
    0.23
     fucking
    0.23
     outpost
    0.23
     positioning
    0.23
    bih
    0.23
    åİĨ
    0.23
    Activations Density 0.064%

    No Known Activations