© 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. 109250
    Prev
    Next
    INDEX
    Explanations

    resources and staffing

    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
    ICLE
    -0.28
    oreal
    -0.26
    acer
    -0.25
    åħ±åIJĮåıijå±ķ
    -0.25
    ADED
    -0.25
     opr
    -0.25
    CoreApplication
    -0.25
    åħĪ导
    -0.25
    å«Į
    -0.24
    æ¸
    -0.24
    POSITIVE LOGITS
     resources
    0.33
    ãĤ¹ãĤ¿ãĥĥãĥķ
    0.30
     staff
    0.29
    staff
    0.28
    èĥ½åĬĽåĴĮ
    0.27
     chairs
    0.27
     billing
    0.26
    Smarty
    0.26
    resources
    0.26
     staffing
    0.26
    Activations Density 0.923%

    No Known Activations