© 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. 149802
    Prev
    Next
    INDEX
    Explanations

    Mot

    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
    оÑģÑĤей
    -0.25
     purchase
    -0.25
    æ°¸ä¹ħ
    -0.25
    ource
    -0.25
    è´Ńä¹°
    -0.24
    pick
    -0.24
     patriotic
    -0.24
    è²·ãģĨ
    -0.24
    ä¸İä¸ŃåĽ½
    -0.23
    æĦ¿æĦı
    -0.23
    POSITIVE LOGITS
    aney
    0.29
    lesia
    0.26
    ä¸ŃæľŁ
    0.25
    dle
    0.24
    æīĭèīº
    0.24
    .um
    0.24
    羸
    0.24
    è¯Į
    0.23
    Ping
    0.23
    eny
    0.23
    Activations Density 0.107%

    No Known Activations