© 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. 23610
    Prev
    Next
    INDEX
    Explanations

    per

    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
    ]int
    -0.27
     Garten
    -0.25
    ï¼Īç¬ij
    -0.25
    åijĢ
    -0.25
    æ¾İ
    -0.25
    orelease
    -0.25
    enberg
    -0.25
    çĶŁçī©
    -0.25
     hå
    -0.25
    YA
    -0.24
    POSITIVE LOGITS
    æīģ
    0.33
    å¹³åĿ¦
    0.27
    icer
    0.26
    ائÙĤ
    0.26
    hay
    0.25
    åĢĴ
    0.25
    åĬŀäºĭ
    0.24
     se
    0.24
    uteur
    0.24
    LEEP
    0.23
    Activations Density 0.002%

    No Known Activations