© 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. 27-TRANSCODER-HP
    7. 8436
    Prev
    Next
    INDEX
    Explanations

    by

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     after
    -0.41
    æĪªæŃ¢
    -0.40
    æĪªèĩ³
    -0.38
     After
    -0.37
    After
    -0.35
    after
    -0.34
    _after
    -0.33
     AFTER
    -0.32
     após
    -0.30
     поÑģле
    -0.29
    POSITIVE LOGITS
    æīĭèħķ
    0.27
    avs
    0.26
    auf
    0.26
    é¢ĦæľŁ
    0.25
     Dice
    0.24
    åıį
    0.24
    /lists
    0.24
    avi
    0.24
    /ion
    0.24
     interpre
    0.23
    Activations Density 0.003%

    No Known Activations