© 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. 15-RESID-POST-AA
    11. 42061
    Prev
    Next
    INDEX
    Explanations

    signal processing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    התאמה
    -0.07
    -gl
    -0.07
     breathed
    -0.07
     clam
    -0.06
    不幸
    -0.06
    קרה
    -0.06
     Pin
    -0.06
     swo
    -0.06
    TouchUpInside
    -0.06
    "%
    -0.06
    POSITIVE LOGITS
    estatus
    0.07
    ece
    0.07
     między
    0.07
     Setter
    0.07
     mentor
    0.07
    continental
    0.07
     purchaser
    0.07
     sender
    0.07
    特斯
    0.07
     captive
    0.06
    Activations Density 0.011%

    No Known Activations