© 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. 109563
    Prev
    Next
    INDEX
    Explanations

    Code and technical content

    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
    Negative Logits
    ç¼¥
    -0.28
    edriver
    -0.27
    ilateral
    -0.25
     policeman
    -0.25
     councillor
    -0.25
    被åĪĹåħ¥
    -0.24
    æłĩé¢ĺ
    -0.24
    è¶ģçĿĢ
    -0.24
    ereal
    -0.24
    ubs
    -0.24
    POSITIVE LOGITS
    ArrayOf
    0.27
    æĸŃ
    0.26
    æ§ģ
    0.25
     scope
    0.25
    Tac
    0.25
    »
    0.25
    è§Ħ模
    0.25
    lÃŃ
    0.24
    angen
    0.24
    管çIJĨå±Ĥ
    0.24
    Activations Density 0.174%

    No Known Activations