© 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. 8230
    Prev
    Next
    INDEX
    Explanations

    Veget

    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
    .TryParse
    -0.27
     demol
    -0.27
    è¾¹
    -0.26
    sandbox
    -0.26
    æĬķæĶ¾
    -0.25
     cat
    -0.25
    ény
    -0.24
    å·²ä¹ħ
    -0.24
    *'
    -0.24
    æľºåĬ¨
    -0.24
    POSITIVE LOGITS
    AIM
    0.27
    imitive
    0.26
    imum
    0.25
    .openConnection
    0.25
    ç»ĵåIJĪ
    0.24
    ÑĢÑİ
    0.24
     litre
    0.24
    ä¿Ŀå®Ī
    0.24
    acic
    0.24
    cer
    0.24
    Activations Density 0.002%

    No Known Activations