© 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. 27-TRANSCODER-HP
    7. 57953
    Prev
    Next
    INDEX
    Explanations

    specific

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    毫ä¸įçĬ¹è±«
    -0.25
    isto
    -0.25
    æľīä¸ĢçĤ¹
    -0.24
    isions
    -0.23
    “Well
    -0.23
    [:-
    -0.23
    atcher
    -0.23
    -ln
    -0.23
    isman
    -0.23
    æĽ´å¤ļçļĦæĺ¯
    -0.23
    POSITIVE LOGITS
     specific
    1.59
    çī¹å®ļ
    1.51
     particular
    1.35
     Specific
    1.25
    specific
    1.21
    Specific
    1.09
    _specific
    1.09
    -specific
    1.08
     certain
    1.05
    pecific
    0.97
    Activations Density 0.002%

    No Known Activations