© 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. 150189
    Prev
    Next
    INDEX
    Explanations

    information, notes, URLs

    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
    ãģĮãģĭ
    -0.26
     storms
    -0.25
     deleg
    -0.24
    ADER
    -0.23
     mornings
    -0.23
     till
    -0.23
    acea
    -0.23
     unfavor
    -0.23
     fright
    -0.23
     mama
    -0.23
    POSITIVE LOGITS
    					↵					↵
    0.27
    å¼ĢæĿ¥
    0.25
    çŃĽæŁ¥
    0.24
    nar
    0.24
    æĿ¥è¯´
    0.24
    ãģĿãĤĮãģŀãĤĮ
    0.23
    çĦ¦
    0.23
    ekte
    0.23
    æķ°æį®åĪĨæŀIJ
    0.23
    è¿Ľåĩºåı£
    0.23
    Activations Density 0.261%

    No Known Activations