© 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. 9018
    Prev
    Next
    INDEX
    Explanations

    1

    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
    å±¹
    -0.29
    强åĬ²
    -0.27
    åĬ©çIJĨ
    -0.26
    éģ¿åŃķ
    -0.25
    强
    -0.25
    ective
    -0.25
    org
    -0.25
    ÑĤи
    -0.25
    èĢ³è¾¹
    -0.25
    alian
    -0.25
    POSITIVE LOGITS
     wars
    0.38
     #{@
    0.30
    æĪĺäºī
    0.30
     politic
    0.30
     war
    0.30
    สà¸ĩà¸Ħราม
    0.29
    -war
    0.29
    大æĪĺ
    0.28
    GenericType
    0.27
    -pol
    0.27
    Activations Density 0.002%

    No Known Activations