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. 15-RESID-POST-AA
    6. 14313
    Prev
    Next
    INDEX
    Explanations

    }

    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
     cumpl
    -0.07
     doivent
    -0.07
    @app
    -0.07
     developing
    -0.07
    装载
    -0.07
    特
    -0.07
    op
    -0.06
    细微
    -0.06
    pto
    -0.06
    流水
    -0.06
    POSITIVE LOGITS
     affiliate
    0.07
     Gin
    0.07
     Iraqi
    0.07
     Rebel
    0.07
     Slave
    0.07
     Players
    0.07
     rval
    0.07
     Cas
    0.07
    吸纳
    0.07
    piring
    0.07
    Activations Density 0.030%

    No Known Activations