© 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. 5926
    Prev
    Next
    INDEX
    Explanations

    metabolomics

    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
     cold
    -0.07
     door
    -0.07
    隻
    -0.07
     Volkswagen
    -0.07
     bus
    -0.06
     biomass
    -0.06
     barred
    -0.06
    ании
    -0.06
     combination
    -0.06
    户籍
    -0.06
    POSITIVE LOGITS
    迩
    0.09
     Desert
    0.07
    عين
    0.07
    /div
    0.07
    大唐
    0.07
    POSITION
    0.07
    簧
    0.07
     ACTIONS
    0.07
    めた
    0.07
    textbox
    0.07
    Activations Density 0.017%

    No Known Activations