© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 46000
    Prev
    Next
    INDEX
    Explanations

    sequence

    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
     side
    -0.07
    crc
    -0.07
    暴露
    -0.06
    	None
    -0.06
     Nếu
    -0.06
     kỷ
    -0.06
    (curr
    -0.06
     did
    -0.06
    "/>
    -0.06
    呼
    -0.06
    POSITIVE LOGITS
     Heath
    0.07
    NTSTATUS
    0.07
     walkers
    0.07
    bet
    0.07
     TOR
    0.07
    ivirus
    0.07
     Copa
    0.07
     ipt
    0.07
     ريال
    0.07
    (hr
    0.07
    Activations Density 0.001%

    No Known Activations