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. 129769
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Slee
    -0.07
     stares
    -0.06
    客厅
    -0.06
    texto
    -0.06
    \r
    -0.06
    conditions
    -0.06
    ubbles
    -0.06
    充值
    -0.06
    三期
    -0.06
    싹
    -0.06
    POSITIVE LOGITS
     défini
    0.07
    そうです
    0.07
     Needed
    0.07
     된다
    0.07
    ,l
    0.07
    欲しい
    0.06
    Needed
    0.06
    .........
    0.06
    posable
    0.06
    ALT
    0.06
    Activations Density 0.003%

    No Known Activations