© 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. 23969
    Prev
    Next
    INDEX
    Explanations

    chain

    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
    éĦ¯
    -0.27
    ctp
    -0.27
    cep
    -0.27
    preload
    -0.25
     shell
    -0.24
    ,rp
    -0.24
    chip
    -0.24
    cept
    -0.24
    ɹ
    -0.24
    dens
    -0.22
    POSITIVE LOGITS
    æĿ¡
    0.36
    Reaction
    0.35
    æ¢Ŀ
    0.33
     reaction
    0.31
    åıįåºĶ
    0.30
     Reaction
    0.30
    reaction
    0.30
    alysis
    0.29
    _reaction
    0.28
     Bars
    0.27
    Activations Density 0.055%

    No Known Activations