© 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. 25-TRANSCODER-HP
    7. 107362
    Prev
    Next
    INDEX
    Explanations

    science

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ely
    -0.28
    affle
    -0.26
    tics
    -0.26
    ureka
    -0.26
    spb
    -0.25
    uras
    -0.25
    ibs
    -0.25
    çļĦæ¦Ĥ念
    -0.25
    worthy
    -0.25
    åīIJ
    -0.24
    POSITIVE LOGITS
    潮湿
    0.30
    湿
    0.27
    æħİ
    0.26
    æ½®
    0.26
    æĶ¯çº¿
    0.26
    æ°¸
    0.25
    æĸ½
    0.24
     eslint
    0.24
     <%=
    0.24
    å¯Ĵ
    0.24
    Activations Density 0.132%

    No Known Activations