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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 19-RESID-POST-AA
    6. 24594
    Prev
    Next
    INDEX
    Explanations

    }

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    decision
    -0.07
     Because
    -0.07
    	Connection
    -0.07
    ('.')[
    -0.07
    (minutes
    -0.07
     meetings
    -0.07
     Ethics
    -0.07
     captain
    -0.07
    建材
    -0.07
    装配式
    -0.07
    POSITIVE LOGITS
    �
    0.07
    им
    0.07
    -time
    0.07
    격
    0.07
    ゾ
    0.07
    سه
    0.07
    _ALL
    0.06
    꺽
    0.06
     MODULE
    0.06
    placeholders
    0.06
    Activations Density 0.002%

    No Known Activations