© 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. 12-TRANSCODER-HP
    7. 22427
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs and language constructs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tag
    -0.26
    æ°Ķæ°Ľ
    -0.25
     relative
    -0.25
     Conf
    -0.24
    çĽ¸å¯¹
    -0.24
    群
    -0.24
    s
    -0.24
    lain
    -0.24
    ologna
    -0.24
    åĨµ
    -0.24
    POSITIVE LOGITS
    æĪij说
    0.27
    apel
    0.27
    phasis
    0.27
    plier
    0.26
    phis
    0.25
    ãģ«ä¹Ĺ
    0.25
    åIJĦ级
    0.25
    pled
    0.25
    pson
    0.24
    phan
    0.24
    Activations Density 0.008%

    No Known Activations