© 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. 57702
    Prev
    Next
    INDEX
    Explanations

    political

    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
     politics
    -0.30
    åĽ½æĥħ
    -0.30
    æĶ¿æ²»
    -0.29
    -aware
    -0.28
    atology
    -0.26
    deo
    -0.25
    ftime
    -0.25
     racism
    -0.25
    metry
    -0.25
    merce
    -0.24
    POSITIVE LOGITS
    é¢Ĩ导èĢħ
    0.28
    èīºæľ¯å®¶
    0.28
    大佬
    0.28
     oppos
    0.27
    gressor
    0.27
    /rfc
    0.27
     paraph
    0.26
    ä¼´ä¾£
    0.25
     leaders
    0.25
    çļĦ帮åĬ©
    0.25
    Activations Density 0.004%

    No Known Activations