© 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. 112152
    Prev
    Next
    INDEX
    Explanations

    won

    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
    _last
    -0.28
     spd
    -0.28
     likelihood
    -0.28
     population
    -0.27
    rego
    -0.26
     collaboration
    -0.26
    çĶŁåij½åĬĽ
    -0.26
     populations
    -0.25
    éĥ½æĥ³
    -0.25
     likely
    -0.25
    POSITIVE LOGITS
    :disable
    0.30
    oste
    0.29
    aron
    0.28
    oster
    0.28
    itone
    0.27
    åIJĮæł·çļĦ
    0.27
    åIJĮ樣
    0.26
    تÙĬ
    0.26
    è¿Ļç§įæĸ¹æ³ķ
    0.26
    æIJºå¸¦
    0.25
    Activations Density 0.004%

    No Known Activations