© 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. 54224
    Prev
    Next
    INDEX
    Explanations

    around

    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
    çļĦä¸Ģ
    -0.25
    è·ŁæĪij说
    -0.24
    åıĪèĥ½
    -0.24
    åĻ¨æ¢°
    -0.24
     device
    -0.24
    æ¯ĶæĪij
    -0.24
    Äĥng
    -0.24
    为ä¸ŃåĽ½
    -0.24
    ↵                        ↵
    -0.24
    cko
    -0.24
    POSITIVE LOGITS
    aim
    0.29
    Nature
    0.26
     Nature
    0.26
     AIM
    0.25
     enjoying
    0.25
     the
    0.25
    nature
    0.25
    inding
    0.24
     aim
    0.24
    -town
    0.24
    Activations Density 0.043%

    No Known Activations