© 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. 11-RESID-POST-AA
    6. 62737
    Prev
    Next
    INDEX
    Explanations

    code

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    泱
    -0.08
     JE
    -0.07
    op
    -0.07
    כנסת
    -0.07
    readcrumbs
    -0.06
     Trilogy
    -0.06
    狰
    -0.06
     Perception
    -0.06
     amassed
    -0.06
    odcast
    -0.06
    POSITIVE LOGITS
    综合治理
    0.07
    修建
    0.06
    �
    0.06
    原件
    0.06
     ############
    0.06
    分销
    0.06
    /year
    0.06
     вход
    0.06
                                                            
    0.06
     리스트
    0.06
    Activations Density 0.026%

    No Known Activations