© 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. 130346
    Prev
    Next
    INDEX
    Explanations

    Island locations

    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
    iciel
    -0.28
    éĺħ读åħ¨æĸĩ
    -0.27
    hec
    -0.26
     dess
    -0.25
    omer
    -0.25
    RD
    -0.25
     compr
    -0.25
    vue
    -0.25
    饶
    -0.24
     ele
    -0.24
    POSITIVE LOGITS
    detach
    0.33
    rors
    0.32
    angles
    0.31
    .detach
    0.30
    趾
    0.28
    ç¾¤å²Ľ
    0.28
    ibraries
    0.27
    boxes
    0.27
    ªĮ
    0.26
    dig
    0.26
    Activations Density 0.008%

    No Known Activations