© 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. 107252
    Prev
    Next
    INDEX
    Explanations

    forms and contact info

    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
    èľ©
    -0.28
    ä¼ļåIJĮ
    -0.26
    '=
    -0.26
    åĪ°è´¦
    -0.25
    产åĩº
    -0.25
    åħĭ
    -0.24
    åĪ°åºķ
    -0.24
    æī©å¤§
    -0.24
    计åĪĴ
    -0.24
     entr
    -0.24
    POSITIVE LOGITS
    nett
    0.26
    yard
    0.26
    schlä
    0.26
    票
    0.26
    mesh
    0.26
    cery
    0.25
    Æ°a
    0.25
     lipstick
    0.25
    itol
    0.24
    "label
    0.24
    Activations Density 0.904%

    No Known Activations