© 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. 27-TRANSCODER-HP
    7. 58026
    Prev
    Next
    INDEX
    Explanations

    unusual characters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pect
    -0.29
    ëĤ¸
    -0.26
    PIO
    -0.26
    ention
    -0.25
    ouncement
    -0.24
    ping
    -0.24
     track
    -0.24
     comet
    -0.24
    .sendStatus
    -0.24
    êt
    -0.24
    POSITIVE LOGITS
    s
    0.26
    ãģĤãĤĭ
    0.25
    -ring
    0.24
    RING
    0.24
    MOST
    0.24
    BUFF
    0.24
    PLICIT
    0.23
    ummy
    0.23
    Æ°u
    0.23
    HI
    0.23
    Activations Density 0.011%

    No Known Activations