© 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. 108088
    Prev
    Next
    INDEX
    Explanations

    lives

    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
    ariant
    -0.28
     rays
    -0.27
    ether
    -0.26
    sville
    -0.26
    éķľå¤´
    -0.26
     signals
    -0.24
    ordial
    -0.24
    çķİ
    -0.23
    osite
    -0.23
    çĪĨ
    -0.23
    POSITIVE LOGITS
    ilos
    0.31
    lug
    0.29
    ä»ĸä»¬åľ¨
    0.28
    FN
    0.27
    åľ¨éĤ£éĩĮ
    0.27
    ocracy
    0.26
    ä»Ģä¹ĪæŶåĢĻ
    0.26
    leave
    0.26
    ployment
    0.25
    elden
    0.24
    Activations Density 0.959%

    No Known Activations