© 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. 24-TRANSCODER-HP
    7. 149995
    Prev
    Next
    INDEX
    Explanations

    code, technical content

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ļ¨
    -0.28
    cams
    -0.27
    æĬŁ
    -0.27
    æ¯ĶåĪ©
    -0.26
    ä¸į解
    -0.26
    igators
    -0.26
    ;++
    -0.25
    åľ©
    -0.25
    æ²¹èħ»
    -0.25
    çī¯
    -0.25
    POSITIVE LOGITS
     divergence
    0.30
     importing
    0.28
     shake
    0.28
     requestOptions
    0.26
     appropriation
    0.25
    è´£ç¼ĸ
    0.25
     import
    0.25
     contraction
    0.24
    xCC
    0.24
     tension
    0.24
    Activations Density 0.900%

    No Known Activations