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. 2279
    Prev
    Next
    INDEX
    Explanations

    left or right

    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
    𝕠
    -0.07
     disrespectful
    -0.07
     sir
    -0.07
     Huang
    -0.07
     בהתאם
    -0.07
     תגובה
    -0.07
    柃
    -0.07
    (edges
    -0.07
    .lastIndexOf
    -0.07
    _Selection
    -0.06
    POSITIVE LOGITS
    BF
    0.07
     discard
    0.07
    VD
    0.07
     клуб
    0.07
    UB
    0.06
     sınav
    0.06
      
    ↵
    0.06
    UTH
    0.06
     Thread
    0.06
    iden
    0.06
    Activations Density 0.003%

    No Known Activations