Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 19-RESID-POST-AA
    6. 70427
    Prev
    Next
    INDEX
    Explanations

    Automotive infotainment systems

    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
    ывает
    -0.08
     dairy
    -0.07
     completo
    -0.07
    既是
    -0.07
     ct
    -0.07
     energía
    -0.07
    ывают
    -0.07
     breaker
    -0.07
    *-
    -0.07
     tercer
    -0.07
    POSITIVE LOGITS
    -have
    0.08
    _SLOT
    0.07
    .fhir
    0.07
    _SPELL
    0.07
    оф
    0.07
    Fran
    0.07
    𝚟
    0.07
    _increase
    0.07
     וי
    0.07
    fusc
    0.07
    Activations Density 0.038%

    No Known Activations