© 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. 108870
    Prev
    Next
    INDEX
    Explanations

    as

    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
    DialogContent
    -0.27
    etically
    -0.27
    ically
    -0.26
    åħħåĪĨ
    -0.26
    lust
    -0.25
    someone
    -0.25
    éģĵå¾·
    -0.25
    .isAuthenticated
    -0.24
    ising
    -0.24
    acist
    -0.24
    POSITIVE LOGITS
    OrNil
    0.27
    è´µ
    0.27
    itar
    0.25
    ynet
    0.25
    ắc
    0.24
    iants
    0.24
     diss
    0.24
    èĬĿåĬłåĵ¥
    0.24
     identical
    0.23
    Æ°á»Ŀ
    0.23
    Activations Density 0.891%

    No Known Activations