© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RESID-POST-AA
    11. 56994
    Prev
    Next
    INDEX
    Explanations

    permit

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (lambda
    -0.07
    /work
    -0.07
     hern
    -0.07
    ("----------------
    -0.07
    我去
    -0.07
    scheduler
    -0.07
    UserID
    -0.07
    _cnt
    -0.07
    almost
    -0.07
     MyApp
    -0.07
    POSITIVE LOGITS
     LI
    0.07
     gearing
    0.07
    —which
    0.07
    Ĥ
    0.07
    Long
    0.06
     soaring
    0.06
    !:
    0.06
    ––
    0.06
     présence
    0.06
    �
    0.06
    Activations Density 0.001%

    No Known Activations