© 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. 97984
    Prev
    Next
    INDEX
    Explanations

    scientific/technical writing

    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
    attr
    -0.28
    è½½
    -0.26
    æıIJ款
    -0.25
     maxX
    -0.25
    ieux
    -0.24
    æĽ°
    -0.24
     carga
    -0.23
    车å±ķ
    -0.23
     charger
    -0.23
     unloaded
    -0.23
    POSITIVE LOGITS
     Terr
    0.25
     abdomen
    0.23
    èĪĪ
    0.23
    воз
    0.23
    /lg
    0.23
    åĹľ
    0.23
    hton
    0.23
     sentinel
    0.22
    è¿ĺä¸į
    0.22
    ithub
    0.22
    Activations Density 0.015%

    No Known Activations