© 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. 23713
    Prev
    Next
    INDEX
    Explanations

    web

    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
    çºłéĶĻ
    -0.29
     Ashe
    -0.27
    osition
    -0.27
    xda
    -0.25
    åIJĪä½ľåįıè®®
    -0.25
    ç´«èī²
    -0.24
    erte
    -0.24
    ijk
    -0.24
    looks
    -0.24
    æĬķèµĦé¡¹çĽ®
    -0.24
    POSITIVE LOGITS
    @RunWith
    0.25
    пиÑģÑĮ
    0.24
    pro
    0.24
    享çĶ¨
    0.24
    çĻ¾åĪĨçĻ¾
    0.24
    Äĥm
    0.23
    -Men
    0.23
    onds
    0.23
    employed
    0.23
     t
    0.23
    Activations Density 0.002%

    No Known Activations