© 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. 97797
    Prev
    Next
    INDEX
    Explanations

    because

    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
    rior
    -0.27
    weis
    -0.26
     Prospect
    -0.26
    æĥł
    -0.26
    管
    -0.25
    ("~/
    -0.25
    è®°å½ķ
    -0.25
    å¦Ĥæŀľæĺ¯
    -0.25
     prospect
    -0.25
    以åīį
    -0.25
    POSITIVE LOGITS
    ä¸Ģç¬ij
    0.29
    æ©Ľ
    0.25
    .unbind
    0.25
     MonoBehaviour
    0.25
    egot
    0.25
     hö
    0.24
    èį
    0.24
    éŀł
    0.24
    urf
    0.24
     Unblock
    0.23
    Activations Density 0.024%

    No Known Activations