© 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. 109003
    Prev
    Next
    INDEX
    Explanations

    problem solving and technical skills

    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
    åı¯è§Ĥ
    -0.32
    æĿ¿
    -0.29
     concealed
    -0.28
     Plate
    -0.28
    _WARNINGS
    -0.26
    omet
    -0.26
    nie
    -0.26
    ny
    -0.25
    éľĩ
    -0.25
    Plate
    -0.24
    POSITIVE LOGITS
    inka
    0.31
    享
    0.28
     &_
    0.27
    –and
    0.27
     adj
    0.26
    ä¸įåıĹ
    0.26
    æĬĢèĥ½
    0.25
    æĬĢèĥ½åŁ¹è®Ń
    0.25
    skill
    0.25
     strategy
    0.25
    Activations Density 1.051%

    No Known Activations