© 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. 109187
    Prev
    Next
    INDEX
    Explanations

    business and marketing texts

    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
    ä¸ĭ游
    -0.27
     oczywiÅĽcie
    -0.25
     downstream
    -0.24
    æī¹
    -0.24
    azole
    -0.24
     Kami
    -0.23
    pta
    -0.23
    무
    -0.23
    çĽij管éĥ¨éŨ
    -0.23
     adverts
    -0.23
    POSITIVE LOGITS
    夫å¦ĩ
    0.29
     couples
    0.29
    ष
    0.27
     couple
    0.27
     therein
    0.27
     Forget
    0.27
     Thorn
    0.27
    apo
    0.26
    uos
    0.26
     budget
    0.25
    Activations Density 0.958%

    No Known Activations