Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 130156
    Prev
    Next
    INDEX
    Explanations

    Opening and closing times

    np_max-act-logits · gemini-2.0-flashTriggered by @majianfei030706
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Pas
    -0.07
    托
    -0.07
    (ticket
    -0.06
     Address
    -0.06
    ston
    -0.06
    angent
    -0.06
     tượng
    -0.06
    という
    -0.06
     kon
    -0.06
    	template
    -0.06
    POSITIVE LOGITS
     Principle
    0.08
     planner
    0.08
    利用您的
    0.07
    헵
    0.07
     Paras
    0.07
     secrecy
    0.07
    平淡
    0.07
    瑾
    0.07
    为其
    0.06
    _ACL
    0.06
    Activations Density 0.058%

    No Known Activations