© 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. 15287
    Prev
    Next
    INDEX
    Explanations

    start

    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
    古老
    -0.09
    唰
    -0.07
     Ty
    -0.07
     pertaining
    -0.07
    +")
    -0.07
    展会
    -0.07
     thầy
    -0.07
     Lights
    -0.07
    סרט
    -0.06
    ҕ
    -0.06
    POSITIVE LOGITS
    +=(
    0.08
    יה
    0.07
    Prefix
    0.07
     авиа
    0.07
    Vector
    0.07
    /day
    0.07
     ledger
    0.07
    setMax
    0.07
    ceeded
    0.07
    航
    0.07
    Activations Density 0.016%

    No Known Activations