© 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. 87149
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
    _exact
    -0.31
     Chapters
    -0.27
    éĶ¤
    -0.27
    ounder
    -0.26
    åĵ¥ä»¬
    -0.26
     founding
    -0.25
    urally
    -0.25
    èĮ§
    -0.25
     fall
    -0.25
    Fall
    -0.25
    POSITIVE LOGITS
    agos
    0.25
    没æĶ¶
    0.25
    acidad
    0.25
    ien
    0.25
     Ven
    0.25
    arez
    0.24
    avors
    0.24
    龸æ°Ķ
    0.24
    约ä¼ļ
    0.24
     stands
    0.23
    Activations Density 0.007%

    No Known Activations