© 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. 57506
    Prev
    Next
    INDEX
    Explanations

    technical and programming topics

    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
    ivor
    -0.25
    afort
    -0.25
    çĭİ
    -0.24
    HeaderCode
    -0.24
     ballot
    -0.24
    ">&#
    -0.24
    æ¶Įåħ¥
    -0.24
     wagon
    -0.24
    JsonValue
    -0.24
    -links
    -0.24
    POSITIVE LOGITS
    null
    0.32
    ãĢħ
    0.31
     vice
    0.30
     convers
    0.28
    Neg
    0.28
    vers
    0.28
    via
    0.27
     Conversely
    0.27
    ERIC
    0.27
    å®Ŀè´Ŀ
    0.26
    Activations Density 0.005%

    No Known Activations