© 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. 57701
    Prev
    Next
    INDEX
    Explanations

    sub-populations in studies

    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
    nil
    -0.35
     guerr
    -0.26
     nil
    -0.26
    人æĢ§
    -0.26
    人å±ħ
    -0.26
    user
    -0.25
    人
    -0.24
    ç¶ļãģįãĤĴèªŃãĤĢ
    -0.24
    	nil
    -0.23
    åĴĮçĿ¦
    -0.23
    POSITIVE LOGITS
    ificate
    0.27
    oris
    0.27
    ouis
    0.26
     racial
    0.26
    IRE
    0.26
    adoras
    0.26
     targ
    0.26
    isphere
    0.26
    illard
    0.26
    ä¸ĢåĪĻ
    0.26
    Activations Density 0.004%

    No Known Activations