© 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. 23-TRANSCODER-HP
    7. 24283
    Prev
    Next
    INDEX
    Explanations

    I

    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
    broken
    -0.26
    jin
    -0.25
    æĶ¯éĺŁ
    -0.24
    åĬ¡
    -0.24
    spath
    -0.24
    sla
    -0.24
    inus
    -0.23
    é»ijæļĹ
    -0.23
    %↵↵
    -0.23
    ested
    -0.23
    POSITIVE LOGITS
    uzzer
    0.26
    adr
    0.25
    RSA
    0.25
     Usa
    0.25
    çĶ³
    0.25
    uche
    0.25
    unami
    0.24
    ä¸ĩ个
    0.24
    ä¹Ĥ
    0.24
    VEN
    0.23
    Activations Density 0.004%

    No Known Activations