© 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. 108149
    Prev
    Next
    INDEX
    Explanations

    consideration

    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
    iona
    -0.27
    kea
    -0.26
    CastException
    -0.25
     punched
    -0.24
    noop
    -0.24
    å°±å¤ŁäºĨ
    -0.24
    Äĩe
    -0.24
    èĻ½çĦ¶
    -0.24
    绿
    -0.24
    xCE
    -0.23
    POSITIVE LOGITS
     consider
    0.55
     Consider
    0.49
    Consider
    0.47
    èĢĥèĻij
    0.45
    consider
    0.40
     consideration
    0.39
    èĢĥæħ®
    0.36
    ear
    0.35
     considered
    0.33
     look
    0.32
    Activations Density 0.940%

    No Known Activations