© 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. 97994
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    èĢĮ对äºİ
    -0.30
    åĽłä¸ºæĪij
    -0.30
    çĶ±æĸ¼
    -0.29
    æĪij以为
    -0.28
    ç»ħ
    -0.27
    ss
    -0.27
    elves
    -0.26
    çĸ½
    -0.26
    uj
    -0.26
    eme
    -0.26
    POSITIVE LOGITS
    amenti
    0.27
     Airways
    0.27
    迺
    0.25
    ä¸Ģç¬ij
    0.25
    éĢģåİ»
    0.24
     sourceMapping
    0.24
    ilate
    0.24
    à¸ĺา
    0.24
    urf
    0.24
    lopedia
    0.23
    Activations Density 0.005%

    No Known Activations