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. 130057
    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
     Sext
    -0.08
    vae
    -0.07
     tù
    -0.07
     bullied
    -0.07
    exercise
    -0.07
     Exercise
    -0.07
     forall
    -0.07
     Ella
    -0.07
     Gets
    -0.07
    dq
    -0.07
    POSITIVE LOGITS
     =>
    0.07
     '%
    0.07
     partition
    0.07
    /",
    0.07
    Political
    0.07
     производ
    0.07
     организ
    0.06
    RANDOM
    0.06
    nivel
    0.06
    同時に
    0.06
    Activations Density 0.006%

    No Known Activations