© 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. 12-TRANSCODER-HP
    7. 23217
    Prev
    Next
    INDEX
    Explanations

    questionnaires and surveys

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    allon
    -0.28
    itim
    -0.27
    éĤ£ä¸ªäºº
    -0.26
    éĤ£äºº
    -0.26
     authored
    -0.25
    ONA
    -0.25
    æ¸ł
    -0.25
     Raised
    -0.25
    uales
    -0.24
    spam
    -0.24
    POSITIVE LOGITS
     stay
    0.28
    æ·±å±Ĥ次
    0.27
    èİĵ
    0.26
    ä½ĵ
    0.26
    å°ijæķ°
    0.25
    è·ĥ
    0.25
    )+(
    0.24
     account
    0.24
    è·³
    0.24
     Affero
    0.23
    Activations Density 0.022%

    No Known Activations