© 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. 11-RESID-POST-AA
    11. 24873
    Prev
    Next
    INDEX
    Explanations

    sharing

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     onset
    -0.08
    ева
    -0.07
    _lock
    -0.07
    ONDON
    -0.07
    sad
    -0.07
    KP
    -0.07
    私服
    -0.07
     Kaplan
    -0.06
    comic
    -0.06
     الط
    -0.06
    POSITIVE LOGITS
     loops
    0.08
    Adjust
    0.07
     ww
    0.07
     consc
    0.07
    ことができます
    0.07
     partager
    0.07
    espère
    0.07
    forth
    0.06
    行动
    0.06
    充分体现
    0.06
    Activations Density 0.025%

    No Known Activations