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. 109962
    Prev
    Next
    INDEX
    Explanations

    estimate

    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
    -threatening
    -0.07
    _allocator
    -0.07
     giành
    -0.07
    bie
    -0.07
    ripper
    -0.07
     UIB
    -0.07
    맵
    -0.06
    不合
    -0.06
    好
    -0.06
     Mob
    -0.06
    POSITIVE LOGITS
    ,'#
    0.08
     junk
    0.07
    						↵
    0.07
    istol
    0.07
    �
    0.07
     제품
    0.07
     Julio
    0.07
     fung
    0.06
     Cork
    0.06
    坍
    0.06
    Activations Density 0.019%

    No Known Activations