© 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. 108558
    Prev
    Next
    INDEX
    Explanations

    religious texts

    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
    ãĢħ
    -0.30
    ö
    -0.29
    éĢļ
    -0.26
     setContent
    -0.25
    oes
    -0.25
     Greatest
    -0.25
    .swt
    -0.25
     subject
    -0.24
    主é¢ĺæķĻèĤ²
    -0.24
     Pract
    -0.24
    POSITIVE LOGITS
    á¿Ĩ
    0.28
     illusions
    0.27
    asma
    0.26
    äºĨä¸Ģæī¹
    0.24
    ä¾Ŀæŧæĺ¯
    0.24
    Ein
    0.24
    让æĤ¨
    0.24
    intr
    0.23
     Humans
    0.23
    äºĨä¸Ģåľº
    0.23
    Activations Density 0.890%

    No Known Activations