© 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. 149861
    Prev
    Next
    INDEX
    Explanations

    coding file headers

    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
    eyes
    -0.31
    eye
    -0.27
     Gins
    -0.26
    æľŃ
    -0.24
    sh
    -0.24
    ey
    -0.24
    缸
    -0.24
     owes
    -0.24
    abel
    -0.23
     Conversation
    -0.23
    POSITIVE LOGITS
    ogh
    0.34
    omething
    0.25
     plane
    0.25
    ç®ĹäºĨ
    0.25
    omap
    0.24
    ington
    0.24
    ä¸ĥæĺŁ
    0.24
    uar
    0.24
    ìķħ
    0.24
    æħ®
    0.24
    Activations Density 0.054%

    No Known Activations