© 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. 97478
    Prev
    Next
    INDEX
    Explanations

    website notices

    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
    jem
    -0.32
     once
    -0.28
    Once
    -0.27
    æ¯ķä¸ļçĶŁ
    -0.26
    桤
    -0.26
    em
    -0.26
     university
    -0.26
    ÑıÑĤ
    -0.26
     them
    -0.24
     Once
    -0.24
    POSITIVE LOGITS
    ounder
    0.31
    æ±°
    0.27
     avail
    0.26
     TableRow
    0.26
    antal
    0.26
    ån
    0.26
    hare
    0.25
     Rows
    0.25
    pora
    0.25
    avail
    0.25
    Activations Density 0.017%

    No Known Activations