© 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. 9049
    Prev
    Next
    INDEX
    Explanations

    Code, foreign languages

    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
    æ²»
    -0.26
    inish
    -0.25
    atch
    -0.25
    ç³ł
    -0.25
    wen
    -0.25
    çģ«
    -0.25
    eya
    -0.25
    çģ«çĤ¬
    -0.24
     ever
    -0.24
    éķ«
    -0.24
    POSITIVE LOGITS
    ä¾Ŀæ³ķ追究
    0.30
    è¡Ģ液循çݯ
    0.27
    ossip
    0.27
    nels
    0.26
     circ
    0.26
    ormap
    0.25
    ersen
    0.25
    å·¡åĽŀ
    0.25
    å¤ļéĩį
    0.24
     choses
    0.24
    Activations Density 0.002%

    No Known Activations