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. 23-RESID-POST-AA
    6. 130413
    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mush
    -0.06
     swapped
    -0.06
    Russ
    -0.06
     clustered
    -0.06
    因此
    -0.06
    pring
    -0.06
     Crush
    -0.06
    specific
    -0.06
     pinterest
    -0.06
     perceive
    -0.06
    POSITIVE LOGITS
     الاجتماع
    0.07
    idades
    0.07
    .secondary
    0.07
     propiedad
    0.06
    DUCTION
    0.06
    ㎍
    0.06
     الصادر
    0.06
    /set
    0.06
    Dt
    0.06
    .As
    0.06
    Activations Density 0.014%

    No Known Activations