© 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. 25184
    Prev
    Next
    INDEX
    Explanations

    body

    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
     iht
    -0.26
    pect
    -0.24
    çįł
    -0.24
     Moy
    -0.24
     Heads
    -0.24
    âİĿ
    -0.23
     Accessed
    -0.23
     Classic
    -0.23
     Moff
    -0.23
    Ñģли
    -0.23
    POSITIVE LOGITS
    åıĤ
    0.27
    为ä¼ģä¸ļ
    0.26
    ationToken
    0.26
    æľ«
    0.25
    èĭ¦
    0.25
    è°¦
    0.25
    åĪĨè¡Į
    0.25
    å¹³åĩ¡
    0.25
    adar
    0.25
     reve
    0.24
    Activations Density 0.028%

    No Known Activations