© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 69362
    Prev
    Next
    INDEX
    Explanations

    question

    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
    หน
    -0.07
    _VM
    -0.07
     recherche
    -0.06
     Alleg
    -0.06
     invite
    -0.06
    兕
    -0.06
    _aes
    -0.06
    izzare
    -0.06
    El
    -0.06
    貸款
    -0.06
    POSITIVE LOGITS
     getResult
    0.09
    三亚
    0.08
    骧
    0.07
    atever
    0.07
     disables
    0.07
    很高的
    0.07
    بقى
    0.07
     bert
    0.07
     أكثر
    0.07
     newX
    0.07
    Activations Density 0.030%

    No Known Activations