© 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. 27-TRANSCODER-HP
    7. 57560
    Prev
    Next
    INDEX
    Explanations

    Code and software

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     process
    -0.54
    process
    -0.53
    è¿ĩç¨ĭ
    -0.49
    -process
    -0.46
     Process
    -0.45
    _process
    -0.44
     processo
    -0.43
    Process
    -0.43
    	process
    -0.42
    éģİç¨ĭ
    -0.41
    POSITIVE LOGITS
    atars
    0.30
    æĦŁåħ´è¶£çļĦ
    0.28
    eway
    0.28
     arrangement
    0.25
    istor
    0.24
    è¿Ļ家
    0.24
    æ¯ıèĤ¡
    0.24
    设置äºĨ
    0.23
    ATAR
    0.23
    家éŨåı£
    0.23
    Activations Density 0.001%

    No Known Activations