© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 107251
    Prev
    Next
    INDEX
    Explanations

    zoom

    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
    æłĭ
    -0.26
    ä¹ĭæĺŁ
    -0.25
     Ñģобой
    -0.24
    æ»Ķ
    -0.24
    serialize
    -0.24
    å®ĺæĸ¹
    -0.24
    亲çĪ±
    -0.23
    serter
    -0.23
    ç»´æĬ¤
    -0.23
    èѦåijĬ
    -0.23
    POSITIVE LOGITS
    ableView
    0.35
    ing
    0.32
    able
    0.31
    istic
    0.30
    ernes
    0.29
    erate
    0.28
    ers
    0.28
    -context
    0.27
    er
    0.27
    iman
    0.25
    Activations Density 0.225%

    No Known Activations