© 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. 108072
    Prev
    Next
    INDEX
    Explanations

    Well

    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
    wa
    -0.28
    RTL
    -0.27
    èĢĮéĿŀ
    -0.27
    criptor
    -0.27
    |R
    -0.26
    å¾Ĺèµ·
    -0.25
    /of
    -0.25
    ä¸įä¸Ĭ
    -0.24
    pled
    -0.24
    ught
    -0.24
    POSITIVE LOGITS
     dag
    0.25
    çĵ¢
    0.25
    表达
    0.24
    aries
    0.24
    è¾
    0.24
    æĨ§æĨ¬
    0.24
     basically
    0.24
    ÑĤÑĥ
    0.23
    è¿ĻéĩĮ
    0.23
     Highlander
    0.23
    Activations Density 0.193%

    No Known Activations