© 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. 39506
    Prev
    Next
    INDEX
    Explanations

    fin

    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
    ä¸įåħį
    -0.27
    ä¸įå¿ĺ
    -0.27
    ä¹¡åľŁ
    -0.25
    éĺ¶çº§
    -0.24
     MGM
    -0.24
     BOTH
    -0.24
    è¯łéĩĬ
    -0.23
    .onActivityResult
    -0.23
    åħ³åĪĩ
    -0.23
     allocations
    -0.23
    POSITIVE LOGITS
    ess
    0.38
    cu
    0.37
    cut
    0.37
    cia
    0.35
    cil
    0.35
    cat
    0.35
    cz
    0.35
    cou
    0.35
    c
    0.34
    cps
    0.34
    Activations Density 0.034%

    No Known Activations