© 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. 23825
    Prev
    Next
    INDEX
    Explanations

    legal claim

    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
    绩
    -0.07
    Exited
    -0.07
    =url
    -0.07
    剩余
    -0.07
     corrective
    -0.06
    助理
    -0.06
    Cancel
    -0.06
     Histogram
    -0.06
     males
    -0.06
     wages
    -0.06
    POSITIVE LOGITS
    使得
    0.08
    CONTROL
    0.08
    難
    0.08
    ċ
    0.07
     öd
    0.07
     intent
    0.07
    -mf
    0.07
    潮
    0.07
    ],
    0.06
    עיון
    0.06
    Activations Density 0.009%

    No Known Activations