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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7319
    Prev
    Next
    INDEX
    Explanations

    conversational/personal text

    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
     DN
    -0.07
    El
    -0.07
    XC
    -0.07
    oyo
    -0.07
     Variant
    -0.07
    appable
    -0.06
     tat
    -0.06
    _partner
    -0.06
     Attributes
    -0.06
     Personnel
    -0.06
    POSITIVE LOGITS
    cake
    0.08
    枷
    0.07
     SceneManager
    0.07
    蹑
    0.07
    文体
    0.07
     nanop
    0.07
     ulaş
    0.07
    	snprintf
    0.07
    ublisher
    0.07
     Shooter
    0.07
    Activations Density 0.182%

    No Known Activations