© 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. 33-TRANSCODER-HP
    7. 53474
    Prev
    Next
    INDEX
    Explanations

    mom

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ayar
    -0.27
    velle
    -0.26
     accum
    -0.25
     rag
    -0.25
     Conc
    -0.24
    æħ£
    -0.24
    outs
    -0.24
    ãĤµãĤ¤
    -0.24
    é£İæ°Ķ
    -0.24
     conv
    -0.24
    POSITIVE LOGITS
    è¡ĮæĶ¿
    0.28
    orch
    0.26
     Pew
    0.26
    æ²ı
    0.25
     shotgun
    0.25
    è¯Ńæ³ķ
    0.25
    åĮħåĽ´
    0.24
    Unsafe
    0.24
    ä¹Ŀåįģ
    0.24
    让æ¶Īè´¹èĢħ
    0.24
    Activations Density 0.008%

    No Known Activations