© 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. 25-TRANSCODER-HP
    7. 107619
    Prev
    Next
    INDEX
    Explanations

    say "since"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .createFrom
    -0.29
    achu
    -0.27
    jie
    -0.26
    æĦıè¯Ĩ
    -0.26
    oS
    -0.25
    æıIJ示
    -0.25
    spin
    -0.25
    ÃŃo
    -0.24
    ADER
    -0.24
    sock
    -0.24
    POSITIVE LOGITS
    设计æĸ¹æ¡Ī
    0.35
     sec
    0.29
    ä¸Ģä¼ļåĦ¿
    0.27
    è¦ļ
    0.25
    ;)
    0.25
     raining
    0.25
    æķĻæ¡Ī
    0.25
     succ
    0.24
    (sec
    0.24
    ivar
    0.24
    Activations Density 0.910%

    No Known Activations