© 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. 23-TRANSCODER-HP
    7. 24554
    Prev
    Next
    INDEX
    Explanations

    studies and research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çŁŃ线
    -0.33
     legitimately
    -0.26
    ikon
    -0.26
    åľºä¸Ĭ
    -0.26
    è¶ģ
    -0.25
    ãĥģãĥ¥
    -0.25
    主线
    -0.24
    idge
    -0.24
    íĮIJ
    -0.24
    лÑij
    -0.24
    POSITIVE LOGITS
    çĥŁ
    0.32
    .Nil
    0.30
     cigarette
    0.30
     smoker
    0.28
     av
    0.27
    åĽŀéģ¿
    0.27
     stain
    0.25
    ponsors
    0.25
    sa
    0.25
    ested
    0.25
    Activations Density 0.005%

    No Known Activations