© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 122996
    Prev
    Next
    INDEX
    Explanations

    LSTM networks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Detection
    -0.07
     בגיל
    -0.07
     بغداد
    -0.07
    徊
    -0.07
     mụ
    -0.06
    جائزة
    -0.06
    Detach
    -0.06
    [ind
    -0.06
    (location
    -0.06
     drugs
    -0.06
    POSITIVE LOGITS
     connectionString
    0.08
     :::
    0.07
    凭证
    0.07
     Raised
    0.07
    =-=-=-=-=-=-=-=-
    0.07
    )(_
    0.07
    砚
    0.07
    看过
    0.07
     creek
    0.07
    经费
    0.07
    Activations Density 0.005%

    No Known Activations