© 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. 89644
    Prev
    Next
    INDEX
    Explanations

    ative

    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
    כס
    -0.07
    صلة
    -0.07
     defends
    -0.07
    (IB
    -0.07
    DOG
    -0.07
     Contractor
    -0.07
    תח
    -0.07
     Northeast
    -0.06
    一點
    -0.06
     himself
    -0.06
    POSITIVE LOGITS
    .publisher
    0.07
    .qty
    0.07
    各项
    0.07
    uffles
    0.07
     ponieważ
    0.07
     logging
    0.07
     Mey
    0.06
    .observable
    0.06
    уницип
    0.06
     reductions
    0.06
    Activations Density 0.002%

    No Known Activations