© 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. 40001
    Prev
    Next
    INDEX
    Explanations

    say "—" words

    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
    <|endoftext|>
    -0.40
     mt
    -0.30
    0
    -0.27
    mt
    -0.27
    -0.26
     bm
    -0.26
     bv
    -0.26
     bw
    -0.26
    2
    -0.25
    fv
    -0.25
    POSITIVE LOGITS
    —I
    0.50
    —but
    0.48
    —he
    0.48
    —it
    0.46
    —the
    0.45
    —they
    0.45
    —an
    0.45
    —we
    0.44
    —you
    0.44
    —if
    0.44
    Activations Density 4.486%

    No Known Activations