© 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. 108927
    Prev
    Next
    INDEX
    Explanations

    not

    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
     cleared
    -0.30
    è°ļ
    -0.26
     ALPHA
    -0.25
    emodel
    -0.25
     thÃŃch
    -0.25
    åı¤åħ¸
    -0.25
    !";č↵
    -0.24
     richer
    -0.24
    berra
    -0.24
    edom
    -0.24
    POSITIVE LOGITS
    é¬
    0.30
     Nova
    0.27
    è¦ģè¿Ľä¸ĢæŃ¥
    0.26
    å¾ĺå¾Ĭ
    0.26
    ständ
    0.26
    çĭ¬ç«ĭ
    0.26
    åħĪè¿Ľ
    0.25
    -sided
    0.25
     perpet
    0.25
    еÑģÑĤи
    0.25
    Activations Density 1.041%

    No Known Activations