© 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. 19-RESID-POST-AA
    6. 5392
    Prev
    Next
    INDEX
    Explanations

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     valves
    -0.08
     entitled
    -0.07
    -value
    -0.07
     ListItem
    -0.07
    SORT
    -0.07
     vertices
    -0.07
     installer
    -0.07
     they
    -0.07
     vy
    -0.07
     phot
    -0.06
    POSITIVE LOGITS
    蘅
    0.07
    ymoon
    0.07
    鬘
    0.07
    _CODES
    0.07
    Ấ
    0.07
    .appcompat
    0.07
     Boeh
    0.06
    ❞
    0.06
     Rewards
    0.06
    еб
    0.06
    Activations Density 0.026%

    No Known Activations