© 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. 24126
    Prev
    Next
    INDEX
    Explanations

    d or de

    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
    åįĬå²Ľ
    -0.29
    ;n
    -0.27
    =format
    -0.27
    idon
    -0.26
    agli
    -0.25
    )n
    -0.25
    æĪIJåĬŁçļĦ
    -0.25
    :maj
    -0.25
    没人
    -0.25
    æĪĺ
    -0.24
    POSITIVE LOGITS
     juicy
    0.25
    åľ¨æ¸¸æĪıä¸Ń
    0.25
    usal
    0.25
     Shields
    0.24
    pto
    0.24
     ahead
    0.24
    ä¸īä½įä¸Ģä½ĵ
    0.23
    ears
    0.23
    çĺ¾
    0.23
    æ¯Ķè¾ĥé«ĺ
    0.22
    Activations Density 0.011%

    No Known Activations