© 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. 22643
    Prev
    Next
    INDEX
    Explanations

    example

    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
     Gan
    -0.08
     gain
    -0.07
     muito
    -0.07
    一丝
    -0.07
     Aber
    -0.07
     Necessary
    -0.07
     Główn
    -0.07
    нее
    -0.06
    因为我
    -0.06
     Gone
    -0.06
    POSITIVE LOGITS
    -----------↵↵
    0.07
    -collection
    0.07
    _YEAR
    0.07
    とりあえず
    0.07
     setting
    0.07
    多种形式
    0.07
    /components
    0.06
     taxa
    0.06
     LJ
    0.06
     strangers
    0.06
    Activations Density 0.020%

    No Known Activations