© 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. 107765
    Prev
    Next
    INDEX
    Explanations

    Previous experience

    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
     Hin
    -0.28
    严峻
    -0.26
    achers
    -0.26
    çİ»çĴĥ
    -0.26
    innen
    -0.25
    ampo
    -0.25
    éĤĢ
    -0.25
    uteur
    -0.24
    ulators
    -0.23
    ppe
    -0.23
    POSITIVE LOGITS
     familiarity
    0.62
     knowledge
    0.59
     prior
    0.59
     expertise
    0.52
    prior
    0.50
     previous
    0.50
    çļĦçŁ¥è¯Ĩ
    0.50
    çŁ¥è¯Ĩ
    0.49
    æĩĤ
    0.49
     background
    0.49
    Activations Density 1.464%

    No Known Activations