© 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. 39763
    Prev
    Next
    INDEX
    Explanations

    Sin

    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
     validity
    -0.29
     valid
    -0.28
     legitimacy
    -0.27
    .valid
    -0.27
    æݨéĶĢ
    -0.26
     blackout
    -0.26
    ä¸Ģéĺµ
    -0.26
     devotion
    -0.25
     dedication
    -0.25
    éĬ®
    -0.25
    POSITIVE LOGITS
    omer
    0.33
    nea
    0.30
    ive
    0.30
    shan
    0.30
    inan
    0.30
    abra
    0.30
    isos
    0.29
    obuf
    0.28
    vince
    0.28
    omes
    0.28
    Activations Density 1.120%

    No Known Activations