© 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. 8799
    Prev
    Next
    INDEX
    Explanations

    there exists

    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
    ãģ£ãģ±
    -0.27
    èĻŀ
    -0.26
    Pager
    -0.25
    äºĶåħŃ
    -0.25
    ãģĭãģijãģ¦
    -0.25
    rze
    -0.25
    .accuracy
    -0.24
    charges
    -0.24
     bucks
    -0.23
     á»ķ
    -0.23
    POSITIVE LOGITS
     finite
    0.38
     tuple
    0.30
    ä¸Ģä¼ļ
    0.29
     Finite
    0.29
    FINITE
    0.28
    ä¸Ģ对
    0.27
    inning
    0.26
     integer
    0.26
    aversable
    0.26
     fin
    0.26
    Activations Density 0.016%

    No Known Activations