© 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. 35-TRANSCODER-HP
    7. 39904
    Prev
    Next
    INDEX
    Explanations

    suffixes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kop
    -0.29
    asso
    -0.28
    auge
    -0.28
    ayers
    -0.28
    rends
    -0.28
    ko
    -0.28
    kle
    -0.28
    heimer
    -0.28
    akers
    -0.27
    amento
    -0.27
    POSITIVE LOGITS
    isc
    0.43
    itic
    0.40
    ict
    0.40
    icted
    0.37
    it
    0.35
    im
    0.35
    ich
    0.35
    ist
    0.34
    itics
    0.34
    istic
    0.34
    Activations Density 9.169%

    No Known Activations