© 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. 35-TRANSCODER-HP
    7. 39557
    Prev
    Next
    INDEX
    Explanations

    The

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¾ĭå¤ĸ
    -0.26
    ï¼Ľ
    -0.25
    loads
    -0.24
    ãĢĤ
    -0.23
    秤
    -0.22
    :
    -0.22
    -License
    -0.22
     PURPOSE
    -0.21
    ;
    -0.21
    atoes
    -0.21
    POSITIVE LOGITS
    gor
    0.25
     further
    0.24
    ch
    0.24
    orie
    0.23
    oir
    0.22
    ä¸įç»ı
    0.22
     Ned
    0.22
    éºĹ
    0.22
    	So
    0.22
    ient
    0.21
    Activations Density 4.051%

    No Known Activations