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. 130345
    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
    fitness
    -0.08
    Pan
    -0.08
    领先
    -0.07
    ibNameOrNil
    -0.07
    Pod
    -0.07
     farklı
    -0.07
     Müdürü
    -0.07
    Mah
    -0.07
    疯狂
    -0.06
    沿海
    -0.06
    POSITIVE LOGITS
     screen
    0.06
    ℰ
    0.06
    	Simple
    0.06
    חש
    0.06
    uC
    0.06
     shell
    0.06
     stab
    0.06
    acters
    0.06
    erot
    0.06
     Rudy
    0.06
    Activations Density 0.000%

    No Known Activations