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. 19-RESID-POST-AA
    6. 5640
    Prev
    Next
    INDEX
    Explanations

    0 or 9

    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
     networking
    -0.07
     mpz
    -0.07
    𝒾
    -0.07
     merchandise
    -0.06
     Elf
    -0.06
    ichi
    -0.06
    
    -0.06
     Fans
    -0.06
    消费品
    -0.06
     modifiers
    -0.06
    POSITIVE LOGITS
    (',')↵
    0.07
    acre
    0.07
    -priced
    0.07
     forc
    0.07
    pixel
    0.07
    --------↵↵
    0.06
     offline
    0.06
    压缩
    0.06
     Universe
    0.06
    toolStrip
    0.06
    Activations Density 0.074%

    No Known Activations