© 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. 9086
    Prev
    Next
    INDEX
    Explanations

    token

    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
    tel
    -0.27
    ariant
    -0.26
    attended
    -0.25
    ersion
    -0.24
     repro
    -0.24
    ỡ
    -0.24
     tấm
    -0.24
    åIJĮä¸Ģ个
    -0.23
    ÑĥÑħ
    -0.22
    ancel
    -0.22
    POSITIVE LOGITS
    kap
    0.29
    ilo
    0.26
     fox
    0.25
    kop
    0.25
     convictions
    0.24
    isseur
    0.24
    墨
    0.24
    æŃ¦å£«
    0.24
    sville
    0.24
    ../
    0.24
    Activations Density 0.044%

    No Known Activations