© 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. 14-TRANSCODER-HP
    7. 40386
    Prev
    Next
    INDEX
    Explanations

    patents and technical procedures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    shed
    -0.33
    åıijå±ķ模å¼ı
    -0.31
    ressive
    -0.30
    æİĴè¡Į
    -0.28
    åıijå±ķä¸Ń
    -0.28
    CAS
    -0.26
    sched
    -0.26
     Guess
    -0.26
    oko
    -0.25
    MZ
    -0.25
    POSITIVE LOGITS
    ear
    0.28
    unnel
    0.27
     wired
    0.25
    æĪĸèĢħåħ¶ä»ĸ
    0.25
     tougher
    0.25
    bour
    0.25
    Cond
    0.24
    proper
    0.24
    atre
    0.24
     Paid
    0.24
    Activations Density 0.382%

    No Known Activations