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. 2908
    Prev
    Next
    INDEX
    Explanations

    hate

    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
    רן
    -0.08
     tom
    -0.08
     Joshua
    -0.07
     sürek
    -0.07
     absorb
    -0.07
    𫖳
    -0.07
     mRNA
    -0.07
    독
    -0.07
    🅦
    -0.07
     [];
    ↵
    -0.07
    POSITIVE LOGITS
    ategory
    0.08
    esper
    0.07
    ~-~-~-~-
    0.07
    身为
    0.06
     وفي
    0.06
    极少
    0.06
     progressive
    0.06
     Spir
    0.06
     impending
    0.06
    agedList
    0.06
    Activations Density 0.002%

    No Known Activations