© 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. 57284
    Prev
    Next
    INDEX
    Explanations

    make

    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
     Mont
    -0.29
    æĹ¥åŃIJ
    -0.26
     observes
    -0.26
    DOMNode
    -0.26
     mont
    -0.25
    ä»ĸ对
    -0.25
     cares
    -0.25
     regard
    -0.25
    çħ§é¡¾
    -0.25
    ä¿¡èµĸ
    -0.24
    POSITIVE LOGITS
    uation
    0.28
    etzt
    0.25
    icl
    0.24
    æĻºåĬĽ
    0.24
    asil
    0.24
    -hard
    0.24
    åĬĽåº¦
    0.23
    ica
    0.23
     Silence
    0.23
    -trained
    0.23
    Activations Density 0.005%

    No Known Activations