© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 162439
    Prev
    Next
    INDEX
    Explanations

    "to be" verb forms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erez
    -0.32
    sert
    -0.29
    éĸĴ
    -0.29
    ekt
    -0.28
    sf
    -0.27
    est
    -0.26
     ache
    -0.25
    ert
    -0.25
    hips
    -0.25
    oser
    -0.25
    POSITIVE LOGITS
     undeniable
    0.27
    æĺµ
    0.26
    æĸ°éĹ»ä¸Ńå¿ĥ
    0.25
     proven
    0.25
    оÑģÑĤей
    0.24
    quiv
    0.24
    HandlerContext
    0.24
     indispensable
    0.24
    ãĤ»ãĥ³ãĤ¿ãĥ¼
    0.23
    Ùģا
    0.23
    Activations Density 0.013%

    No Known Activations