© 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. 25-TRANSCODER-HP
    7. 108805
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ertools
    -0.27
    isters
    -0.27
    ä¸įå¾Ĺå·²
    -0.27
    è¹Ļ
    -0.27
    åľ°éģĵ
    -0.26
    missible
    -0.26
    ä½ķåĨµ
    -0.26
    metrical
    -0.26
     whereas
    -0.25
     Whereas
    -0.25
    POSITIVE LOGITS
    \Blueprint
    0.28
    antor
    0.27
     quarter
    0.26
    aj
    0.26
    usch
    0.26
    åIJ¯ç¤º
    0.25
    -quarter
    0.24
    zac
    0.24
    çī¹çĤ¹
    0.24
    æĻĬ
    0.24
    Activations Density 1.017%

    No Known Activations