© 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. 14-TRANSCODER-HP
    7. 40455
    Prev
    Next
    INDEX
    Explanations

    Negative situations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imes
    -0.26
    çĶľçĶľ
    -0.25
    ä½ķ度
    -0.25
    imat
    -0.25
     facult
    -0.24
    ities
    -0.24
    Persistent
    -0.24
    æ¯Ķçİĩ
    -0.23
    ories
    -0.23
    landers
    -0.23
    POSITIVE LOGITS
    ä½Ĩå®ŀéĻħä¸Ĭ
    0.28
    UGE
    0.26
    ARRAY
    0.25
    ÑģÑĤеÑĢ
    0.25
    èİ·å¾ĹäºĨ
    0.24
     lẫn
    0.24
    åģļ大åģļ强
    0.24
    nage
    0.23
    æݧ
    0.23
    èĢĥä¸Ĭ
    0.23
    Activations Density 1.309%

    No Known Activations