© 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. 9-TRANSCODER-HP
    7. 29791
    Prev
    Next
    INDEX
    Explanations

    blood cell production

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ige
    -0.27
    线ä¸ĭ
    -0.26
    æ¼Ĥ
    -0.25
    (ec
    -0.25
     lã
    -0.25
    Rare
    -0.25
    夥
    -0.25
    çĬģ
    -0.24
     Looking
    -0.24
     Vern
    -0.24
    POSITIVE LOGITS
    ifar
    0.27
     freeway
    0.26
    å®īå®ļ
    0.25
    ovsky
    0.25
    åħĪæĬĬ
    0.24
    iner
    0.24
    ARR
    0.24
    æĺİçŁ¥
    0.24
    ola
    0.24
    ktor
    0.24
    Activations Density 0.284%

    No Known Activations