© 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
    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. 1252
    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
    _bc
    -0.09
     axs
    -0.08
    شمل
    -0.08
    _episode
    -0.07
     Projectile
    -0.07
    曈
    -0.06
    拯救
    -0.06
     наз
    -0.06
     s
    -0.06
    诉
    -0.06
    POSITIVE LOGITS
    Ana
    0.08
     Veronica
    0.08
     biologist
    0.07
    。“
    0.07
     las
    0.07
    里面有
    0.07
    oriasis
    0.07
     exhausted
    0.07
    ORIA
    0.06
    ляет
    0.06
    Activations Density 0.000%

    No Known Activations