© 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. 130529
    Prev
    Next
    INDEX
    Explanations

    arrive

    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
    èĪĨ
    -0.27
    æĶ¿åĬ¡
    -0.25
    amines
    -0.25
    åıijçĶŁåľ¨
    -0.24
    æ²Ķ
    -0.24
     APS
    -0.23
     attrs
    -0.23
    amine
    -0.23
    å¤Ł
    -0.23
    liner
    -0.23
    POSITIVE LOGITS
     phá»iji
    0.24
     true
    0.24
    lock
    0.24
    æł¼å±Ģ
    0.23
    REA
    0.23
    robe
    0.23
    ong
    0.23
    ounter
    0.23
     plum
    0.23
    æĬ¢éĻ©
    0.22
    Activations Density 0.318%

    No Known Activations