© 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. 150607
    Prev
    Next
    INDEX
    Explanations

    Iran

    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
     Pipe
    -0.28
    èĥª
    -0.27
     géné
    -0.24
     ep
    -0.24
    åī¯ä¸»ä»»
    -0.24
     coping
    -0.23
    idth
    -0.23
    quier
    -0.23
     presente
    -0.23
    gener
    -0.23
    POSITIVE LOGITS
    enstein
    0.29
    fld
    0.28
    çijľ
    0.28
    quette
    0.26
    urn
    0.26
    建åĨĽ
    0.25
    oin
    0.25
    ewolf
    0.24
    æŃ¥åħ¥
    0.24
     Sinai
    0.23
    Activations Density 0.362%

    No Known Activations