© 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. 27-TRANSCODER-HP
    7. 58024
    Prev
    Next
    INDEX
    Explanations

    say "to"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rist
    -0.24
    udas
    -0.24
     pronounce
    -0.24
    iram
    -0.24
     ÐĹна
    -0.24
    åıijéŁ³
    -0.23
     NYT
    -0.23
     üz
    -0.23
    ÑĢиÑģÑĤ
    -0.23
     Ãĸz
    -0.23
    POSITIVE LOGITS
    æī©
    0.31
    ye
    0.28
    èľķ
    0.25
    leftJoin
    0.25
    cu
    0.24
    åİĿ
    0.24
     av
    0.24
    ä¾
    0.23
    atives
    0.23
    æ¶ķ
    0.23
    Activations Density 0.006%

    No Known Activations