© 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. 24-TRANSCODER-HP
    7. 150860
    Prev
    Next
    INDEX
    Explanations

    Programming/Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ientes
    -0.27
    åºıåĪĹ
    -0.26
    åİŁå§ĭ
    -0.24
    ahun
    -0.24
    rush
    -0.24
    chts
    -0.24
    ÑĩÑijÑĤ
    -0.24
    ä¾ģ
    -0.23
     gam
    -0.23
    iao
    -0.23
    POSITIVE LOGITS
    ä¸Ģ大æī¹
    0.28
    åĪĨæł¡
    0.27
     onstage
    0.27
     reimb
    0.27
    lifting
    0.26
    æķ£åıijçĿĢ
    0.25
    vertime
    0.25
    ervoir
    0.25
    åĨĴçĿĢ
    0.25
    å¼ĢåĬŀ
    0.24
    Activations Density 1.060%

    No Known Activations